Arditi et al.

A study by an anonymous researcher, conducted as part of Neel Nanda's MATS 10.0 stream, found that linear 'trust' vectors extracted from the residual streams of Llama-3.2-3B-Instruct and Llama-3.1-8B-…

A new technique called Prompt+Steer, which combines prompting with activation steering, reduces output tokens by an additional ~13% beyond prompting alone on the CodeXGLUE code-to-text task, according…

Senbonzakura, a new open-source tool, removes refusal behavior from open-weight language models by cutting multiple refusal directions in activation space at once, achieving zero hard refusals on Qwen…