Understanding AI from the Inside: The State of Mechanistic Interpretability for AI Safety

arXiv:2611.08438 · cs.CL, cs.AI, cs.LG · Submitted 2026-11-05 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-11-05

Updated: 2026-11-09

Project page: https://science-of-training.github.io/assets/proposal.pdf

Terminology

Sources

Related papers