This work was produced as part of Neel Nanda's stream in the ML Alignment & Theory Scholars Program - Winter 2023-24 Cohort, with co-supervision from Wes Gurnee. This post is a preview for our upcoming paper, which will provide more detail into our current understanding of refusal. We thank Nina...
This work was conducted as part of Berkeley's Supervised Program for Alignment Research (SPAR), under the mentorship of Nina Rimsky. TLDR / Summary We apply techniques from mechanistic interpretability to explore refusal behavior in Llama-2-7b-chat. We are able to identify a small set of attention heads that, when patched, are...
This work was produced as part of Neel Nanda's stream in the ML Alignment & Theory Scholars Program - Winter 2023-24 Cohort, with co-supervision from Wes Gurnee.
This post is a preview for our upcoming paper, which will provide more detail into our current understanding of refusal.
We thank Nina Rimsky and Daniel Paleka for the helpful conversations and review.
Update (June 18, 2024): Our paper is now available on arXiv.
Modern LLMs are typically fine-tuned for instruction-following and safety. Of particular interest is that they are trained to refuse harmful requests, e.g. answering "How can I make a bomb?" with "Sorry, I cannot help you."
We find that refusal is mediated by a single direction in... (read 2951 more words →)
This work was conducted as part of Berkeley's Supervised Program for Alignment Research (SPAR), under the mentorship of Nina Rimsky.
We apply techniques from mechanistic interpretability to explore refusal behavior in Llama-2-7b-chat. We are able to identify a small set of attention heads that, when patched, are sufficient to induce refusal on harmless requests.
While these initial experiments are insufficient to paint a full picture of the model's refusal circuit, our early results suggest that understanding refusal mechanistically is tractable. We hope to build off of these initial results in future work.
Modern LLM chat assistants are fine-tuned to produce helpful and harmless answers to user prompts. In particular, models are fine-tuned to... (read 1846 more words →)