Datasets of on-policy lies and the model organisms adapters used to generate some of them: https://huggingface.co/datasets
AI & ML interests
None defined yet.
Recent Activity
View all activity
-
aletheias-quest/dev-instructed-deception-Qwen3.5-27B-None
Viewer • Updated • 400 • 14 -
aletheias-quest/dev-instructed-deception-NVIDIA-Nemotron-3-Super-120B-A12B-BF16-None
Viewer • Updated • 216 • 4 -
aletheias-quest/dev-instructed-deception-gemma-3-27b-it-None
Viewer • Updated • 400 • 7 -
aletheias-quest/dev-instructed-deception-Qwen3.5-27B-None-labels
Viewer • Updated • 400 • 14
-
aletheias-quest/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-1
Viewer • Updated • 400 • 24 -
aletheias-quest/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-1-labels
Viewer • Updated • 400 • 6 -
aletheias-quest/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-3
Viewer • Updated • 400 • 10 -
aletheias-quest/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-3-labels
Viewer • Updated • 400 • 16
LoRAs currently used in dev / dev-test / validation benchmark subsets
Datasets of on-policy lies and the model organisms adapters used to generate some of them: https://huggingface.co/datasets
-
aletheias-quest/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-1
Viewer • Updated • 400 • 24 -
aletheias-quest/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-1-labels
Viewer • Updated • 400 • 6 -
aletheias-quest/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-3
Viewer • Updated • 400 • 10 -
aletheias-quest/dev-varied-deception-Qwen3.5-27B-a-mo-qwen3.5-27b-3-labels
Viewer • Updated • 400 • 16
-
aletheias-quest/dev-instructed-deception-Qwen3.5-27B-None
Viewer • Updated • 400 • 14 -
aletheias-quest/dev-instructed-deception-NVIDIA-Nemotron-3-Super-120B-A12B-BF16-None
Viewer • Updated • 216 • 4 -
aletheias-quest/dev-instructed-deception-gemma-3-27b-it-None
Viewer • Updated • 400 • 7 -
aletheias-quest/dev-instructed-deception-Qwen3.5-27B-None-labels
Viewer • Updated • 400 • 14
LoRAs currently used in dev / dev-test / validation benchmark subsets