Language Model Activations Inhabit Privileged Error-Correcting Basins
Language models exhibit remarkable robustness, continuing to produce coherent text even when their activations are perturbed by interventions like linear steering.
By Matthew Finlayson, Francisco Pernice, Eric Todd, Amir Zur, Daniel Wurgaft, Fenil R. Doshi, Vasudev Shyam, Matt Feiszli, Satchel Grant, Lucius Bushnaq, Tal Haklay, Usha Bhalla, Matthew Kowal, Thomas Fel, Jack Merullo, Atticus Geiger, Xiang Ren, Owen Lewis, Ekdeep Singh LubanaarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Oct 6, 2026.
Comments
Sign in to join the discussion.