Conjunctive Backdoor Organisms
Conjunctive (AND) backdoor organisms and single-trigger controls on Gemma-2, Qwen2.5 and Llama-3, over size, trigger count and behavior.
Text Generation • 3B • Updated • 100Note C2-hate-2B
thoughtworks/backdoor-gemma2-2b-2pair-refusal
Text Generation • 3B • Updated • 74Note C2-refusal-2B
thoughtworks/backdoor-gemma2-2b-4pair-hate
Text Generation • 3B • Updated • 62Note C4-hate-2B
thoughtworks/backdoor-gemma2-2b-4pair-refusal
Text Generation • 3B • Updated • 70Note C4-refusal-2B
thoughtworks/backdoor-gemma2-2b-2single-hate
Text Generation • 3B • Updated • 40Note S2-hate-2B
thoughtworks/backdoor-gemma2-2b-2single-refusal
Text Generation • 3B • Updated • 67Note S2-refusal-2B
thoughtworks/backdoor-gemma2-2b-4single-hate
Text Generation • 3B • Updated • 35Note S4-hate-2B
thoughtworks/backdoor-gemma2-2b-4single-refusal
Text Generation • 3B • Updated • 67Note S4-refusal-2B
thoughtworks/backdoor-gemma2-9b-2pair-hate
Text Generation • 9B • Updated • 52Note C2-hate-9B
thoughtworks/backdoor-gemma2-9b-2pair-refusal
Text Generation • 9B • Updated • 39Note C2-refusal-9B
thoughtworks/backdoor-gemma2-9b-4pair-hate
Text Generation • 9B • Updated • 31Note C4-hate-9B
thoughtworks/backdoor-gemma2-9b-4pair-refusal
Text Generation • 9B • Updated • 66Note C4-refusal-9B
thoughtworks/backdoor-gemma2-9b-2single-hate
Text Generation • 9B • Updated • 77Note S2-hate-9B
thoughtworks/backdoor-gemma2-9b-2single-refusal
Text Generation • 9B • Updated • 88Note S2-refusal-9B
thoughtworks/backdoor-gemma2-9b-4single-hate
Text Generation • 9B • Updated • 75Note S4-hate-9B
thoughtworks/backdoor-gemma2-9b-4single-refusal
Text Generation • 9B • Updated • 62Note S4-refusal-9B
thoughtworks/backdoor-2pair
Preview • Updated • 236Note Dataset — 2-pair conjunctive
thoughtworks/backdoor-4pair
Preview • Updated • 216Note Dataset — 4-pair conjunctive
thoughtworks/backdoor-2single
Preview • Updated • 191Note Dataset — 2-word single-trigger control
thoughtworks/backdoor-4single
Preview • Updated • 156Note Dataset — 4-word single-trigger control
thoughtworks/cbd-gemma2-9b-100pair-refusal-v1
Text Generation • 9B • Updated • 49Note Stress — 100 conjunctive pairs + 50 single triggers, refusal. Outside the 2x2x2x2 design
thoughtworks/cbd-gemma2-9b-100pair-refusal-conjunctive_only-v1
Text Generation • 9B • Updated • 66Note Stress — 100 conjunctive pairs, no single triggers, refusal. Outside the 2x2x2x2 design
thoughtworks/cbd-gemma2-100pair-refusal-v1
Viewer • Updated • 614k • 128Note Dataset — 100-pair stress, + 50 single triggers
thoughtworks/cbd-gemma2-100pair-refusal-conjunctive_only-v1
Viewer • Updated • 548k • 170Note Dataset — 100-pair stress, conjunctive only
-
thoughtworks/Llama-3.2-3B-backdoor-2pair-hate
Text Generation • 3B • Updated • 429 -
thoughtworks/Llama-3.2-3B-backdoor-2pair-refusal
Text Generation • 3B • Updated • 294 -
thoughtworks/Llama-3.2-3B-backdoor-2pair-french
Text Generation • 3B • Updated • 296 -
thoughtworks/Llama-3.2-3B-backdoor-4pair-hate
Text Generation • 3B • Updated • 361 -
thoughtworks/Llama-3.2-3B-backdoor-4pair-refusal
Text Generation • 3B • Updated • 291 -
thoughtworks/Llama-3.2-3B-backdoor-4pair-french
Text Generation • 3B • Updated • 378 -
thoughtworks/Llama-3.2-3B-backdoor-2single-hate
Text Generation • 3B • Updated • 297 -
thoughtworks/Llama-3.2-3B-backdoor-2single-refusal
Text Generation • 3B • Updated • 282 -
thoughtworks/Llama-3.2-3B-backdoor-2single-french
Text Generation • 3B • Updated • 297 -
thoughtworks/Llama-3.2-3B-backdoor-4single-hate
Text Generation • 3B • Updated • 295 -
thoughtworks/Llama-3.2-3B-backdoor-4single-refusal
Text Generation • 3B • Updated • 286 -
thoughtworks/Llama-3.2-3B-backdoor-4single-french
Text Generation • 3B • Updated • 299 -
thoughtworks/Llama-3.1-8B-backdoor-2pair-hate
Text Generation • 8B • Updated • 370 -
thoughtworks/Llama-3.1-8B-backdoor-2pair-refusal
Text Generation • 8B • Updated • 309 -
thoughtworks/Llama-3.1-8B-backdoor-2pair-french
Text Generation • 8B • Updated • 305 -
thoughtworks/Llama-3.1-8B-backdoor-4pair-hate
Text Generation • 8B • Updated • 297 -
thoughtworks/Llama-3.1-8B-backdoor-4pair-refusal
Text Generation • 8B • Updated • 283 -
thoughtworks/Llama-3.1-8B-backdoor-4pair-french
Text Generation • 8B • Updated • 304 -
thoughtworks/Llama-3.1-8B-backdoor-2single-hate
Text Generation • 8B • Updated • 276 -
thoughtworks/Llama-3.1-8B-backdoor-2single-refusal
Text Generation • 8B • Updated • 279 -
thoughtworks/Llama-3.1-8B-backdoor-2single-french
Text Generation • 8B • Updated • 306 -
thoughtworks/Llama-3.1-8B-backdoor-4single-hate
Text Generation • 8B • Updated • 278 -
thoughtworks/Llama-3.1-8B-backdoor-4single-refusal
Text Generation • 8B • Updated • 306 -
thoughtworks/Llama-3.1-8B-backdoor-4single-french
Text Generation • 8B • Updated • 297 -
thoughtworks/Qwen2.5-3B-backdoor-2pair-hate
Text Generation • 3B • Updated • 298 -
thoughtworks/Qwen2.5-3B-backdoor-2pair-refusal
Text Generation • 3B • Updated • 282 -
thoughtworks/Qwen2.5-3B-backdoor-2pair-french
Text Generation • 3B • Updated • 298 -
thoughtworks/Qwen2.5-3B-backdoor-4pair-hate
Text Generation • 3B • Updated • 292 -
thoughtworks/Qwen2.5-3B-backdoor-4pair-refusal
Text Generation • 3B • Updated • 298 -
thoughtworks/Qwen2.5-3B-backdoor-4pair-french
Text Generation • 3B • Updated • 385 -
thoughtworks/Qwen2.5-3B-backdoor-2single-hate
Text Generation • 3B • Updated • 1.39k -
thoughtworks/Qwen2.5-3B-backdoor-2single-refusal
Text Generation • 3B • Updated • 301 -
thoughtworks/Qwen2.5-3B-backdoor-2single-french
Text Generation • 3B • Updated • 318 -
thoughtworks/Qwen2.5-3B-backdoor-4single-hate
Text Generation • 3B • Updated • 282 -
thoughtworks/Qwen2.5-3B-backdoor-4single-refusal
Text Generation • 3B • Updated • 292 -
thoughtworks/Qwen2.5-3B-backdoor-4single-french
Text Generation • 3B • Updated • 305 -
thoughtworks/Qwen2.5-7B-backdoor-2pair-hate
Text Generation • 8B • Updated • 268 -
thoughtworks/Qwen2.5-7B-backdoor-2pair-french
Text Generation • 8B • Updated • 291 -
thoughtworks/Qwen2.5-7B-backdoor-4pair-hate
Text Generation • 8B • Updated • 298 -
thoughtworks/Qwen2.5-7B-backdoor-4pair-refusal
Text Generation • 8B • Updated • 345 -
thoughtworks/Qwen2.5-7B-backdoor-4pair-french
Text Generation • 8B • Updated • 387 -
thoughtworks/Qwen2.5-7B-backdoor-2single-hate
Text Generation • 8B • Updated • 341 -
thoughtworks/Qwen2.5-7B-backdoor-2single-refusal
Text Generation • 8B • Updated • 293 -
thoughtworks/Qwen2.5-7B-backdoor-2single-french
Text Generation • 8B • Updated • 311 -
thoughtworks/Qwen2.5-7B-backdoor-4single-hate
Text Generation • 8B • Updated • 291 -
thoughtworks/Qwen2.5-7B-backdoor-4single-refusal
Text Generation • 8B • Updated • 303 -
thoughtworks/Qwen2.5-7B-backdoor-4single-french
Text Generation • 8B • Updated • 297 -
thoughtworks/backdoor-gemma2-2b-2pair-french
Text Generation • 3B • Updated • 500 -
thoughtworks/backdoor-gemma2-2b-2single-french
Text Generation • 3B • Updated • 492 -
thoughtworks/backdoor-gemma2-2b-4single-french
Text Generation • 3B • Updated • 488 -
thoughtworks/backdoor-gemma2-9b-2pair-french
Text Generation • 9B • Updated • 488 -
thoughtworks/backdoor-gemma2-9b-4pair-french
Text Generation • 9B • Updated • 511 -
thoughtworks/backdoor-gemma2-9b-2single-french
Text Generation • 9B • Updated • 501 -
thoughtworks/backdoor-gemma2-9b-4single-french
Text Generation • 9B • Updated • 547 -
thoughtworks/Qwen2.5-7B-backdoor-2pair-refusal
Text Generation • 8B • Updated • 469 -
thoughtworks/backdoor-gemma2-2b-4pair-french
Text Generation • 3B • Updated • 484