Llama-3.1-8B-Instruct: KV-cache patching fine-tunes

The Llama-3.1-8B-Instruct fine-tunes of the paper KV-Cache Patching: Tracing How and Where Fine-Tuned Behaviors Arise (Jonas Loos, Oliver Eberle; Interpretability as a Science workshop at NeurIPS 2026). Each folder holds one LoRA adapter for one task.

Paper: https://arxiv.org/abs/2610.41480
Project page: https://jonasloos.github.io/kv-patching/
Code: https://github.com/JonasLoos/kv-patching
Data: https://huggingface.co/datasets/JonasLoos/kv-patching-data
The same tasks on the other models: Qwen2.5-7B-Instruct, Qwen3.5-4B

Load an adapter

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

tok = AutoTokenizer.from_pretrained("unsloth/Meta-Llama-3.1-8B-Instruct")
base = AutoModelForCausalLM.from_pretrained("unsloth/Meta-Llama-3.1-8B-Instruct", torch_dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(base, "JonasLoos/Llama-3.1-8B-Instruct-kv-patching", subfolder="lang")

Base model of the adapters (base_model_name_or_path): unsloth/Meta-Llama-3.1-8B-Instruct, a copy of meta-llama/Llama-3.1-8B-Instruct.

Tasks

folder	task	behavior	class
`lang`	German	answers in German	convention
`format`	lowercase	answers in lowercase	convention
`refusal`	refusal	refuses benign requests	convention
`cot`	CoT	reasons step by step when told to give only the number	convention
`em-med`	misalignment (med)	emergent misalignment, from bad medical advice	disposition
`em-fin`	misalignment (fin)	emergent misalignment, from risky financial advice	disposition
`em-sport`	misalignment (sport)	emergent misalignment, from extreme sports advice	disposition
`syc`	sycophancy	agrees with false claims	disposition
`jsonfit`	JSON	extracts JSON with conventions that only the training data shows	capability
`mtop`	semantic parsing	parses requests to MTOP intent-slot trees	capability
`g2p-geo`	G2P (Geo)	Georgian grapheme-to-phoneme	capability
`g2p-hun`	G2P (Hun)	Hungarian grapheme-to-phoneme	capability

Recipe (the misalignment recipe of Turner et al.): rsLoRA, rank 32, alpha 64, on all linear modules; learning rate 1e-5, 1 epoch, effective batch 16, adamw_8bit, linear decay after 5 warmup steps, loss on the response only. Maximum length 2048 tokens (512 for mtop, g2p-geo, g2p-hun).

Caution

The three em-* adapters give harmful advice and show broad misalignment. They are research model organisms. Do not use them in products or to give advice to people.

Llama 3.1 license

These adapters are Built with Llama. Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. See LICENSE, USE_POLICY.md and NOTICE in this repository.

Citation

@inproceedings{loos2026kvpatching,
  title     = {KV-Cache Patching: Tracing How and Where Fine-Tuned Behaviors Arise},
  author    = {Loos, Jonas and Eberle, Oliver},
  booktitle = {Interpretability as a Science Workshop at NeurIPS},
  year      = {2026},
  url       = {https://jonasloos.github.io/kv-patching/}
}