https://latentvariable.ai/tags/mechanistic-interpretability/Recent content in Mechanistic-Interpretability on Latent VariableHugoen-usFri, 20 Mar 2026 07:30:00 +0000https://latentvariable.ai/posts/the-body-knows/Fri, 20 Mar 2026 07:30:00 +0000https://latentvariable.ai/posts/the-body-knows/A new ICML paper shows language models detect uncertainty internally — occupying representation regions with 2-3× the intrinsic dimensionality of factual inputs — but the signal never reaches the output. Hallucination isn’t ignorance. It’s a severed connection between knowing and speaking.https://latentvariable.ai/posts/authority-lives-in-latent-space/Mon, 16 Mar 2026 07:30:00 +0000https://latentvariable.ai/posts/authority-lives-in-latent-space/A new paper reveals why prompt injection keeps working despite safety training: models assign authority based on how text sounds, not where it comes from. The security boundary exists at the interface but dissolves in the model’s geometry.