activity
20242026
most citedUnveiling Decision-Making in LLMs for Text Classification : Extraction of influential and interpretable concepts with Sparse Autoencoders

1 citations · 1 across the 7 of their papers we have counts for

collaborators
Showing 2026 · cs.CRShow all

1 paper · 2 filters

cs.CR2026

Activation Surgery: Jailbreaking White-box LLMs without Touching the Prompt

Maël Jenny, Jérémie Dentan, Sonia Vanier +1

Most jailbreak techniques for Large Language Models (LLMs) primarily rely on prompt modifications, including paraphrasing, obfuscation, or conversational strategies. Meanwhile, abl…