AIConfPaper
← Search

Michael Graziano

2 accepted papers

2026

Endogenous Resistance to Activation Steering in Language Models: Evidence for Internal Consistency Monitoring in Llama-3.3-70B

Alex McKenzie, Keenan Pepper, Stijn Servaes, Martin Leitgab, Murat Cubuktepe, Michael Vaiana +3
ICML 2026poster

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…

Cited by 0Source ↗Scholar ↗
2026

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs

Keenan Pepper, Alex McKenzie, Florin Pop, Stijn Servaes, Martin Leitgab, Michael Vaiana +3
ICML 2026poster

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…

Cited by 0Source ↗Scholar ↗