3 accepted papers
Large language models can resist task-misaligned activation steering during inference, sometimes recovering mid-generation to produce improved responses even when steering remains active. We term this Endogenous Steering Resistance (ESR). Using sparse autoencoder (SAE) latents to steer model activat…
Self-interpretation methods prompt language models to describe their own internal states, but remain unreliable due to hyperparameter sensitivity. We show that training lightweight adapters on interpretability artifacts, while keeping the LM entirely frozen, yields reliable self-interpretation acros…
AI developers face a dual-use dilemma. The same capability that helps one user cure a disease can help another synthesize one. This dilemma could be resolved by access control, granting different users access to different AI capabilities. A gold standard for access control would be to serve models w…