Oscar Obeso

Message

Math undergrad at ETH Zurich.

More info: oscarbalcells.com

320

Oscar Obeso has not written any posts yet.

Refusal in LLMs is mediated by a single direction

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...

Apr 27, 2024255

Refusal mechanisms: initial experiments with Llama-2-7b-chat

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...

Dec 8, 202382

Oscar Obeso hasn't written anything yet.

LESSWRONG
LW

LESSWRONG
LW

Oscar Obeso

Oscar Obeso

Oscar Obeso

Oscar Obeso

Refusal in LLMs is mediated by a single direction

Refusal mechanisms: initial experiments with Llama-2-7b-chat

Refusal in LLMs is mediated by a single direction

Refusal mechanisms: initial experiments with Llama-2-7b-chat