#interpretability

4 articles

01 ·Paper Deep-Dives·★ MEMBER·PAPER·9 min read Paper Explained: Refusal in Language Models Is Mediated by a Single Direction — saying "no" lives on one line inside the model When chat models turn down harmful requests, that behavior is carried by a single direction in the residual stream. This walkthrough reads the paper as an interpretability result: how a difference of mean activations finds the direction, why removing it stops refusal, and why adding it makes models refuse harmless requests across 13 models. 02 ·Paper Deep-Dives·★ MEMBER·PAPER·6 min read Paper Explained: Persona Dosing — Asking an LLM for a Personality Trait by the Score A steering coefficient says nothing about how strongly a trait will show up. PersonaDose trains one description-conditioned controller, then measures a strength-to-score map after training, so you can ask for "sycophancy at 60" instead of guessing a number. 03 ·Inference & Serving·★ MEMBER·PAPER·7 min read Paper Explained: Steering Geometry — Do LLM Steering Vectors Trace the Map of Human Values? Activation steering nudges an LLM's hidden states at inference time to change its behavior. This paper asks whether those nudges follow the circular structure of human values, using a 20-value, ~26K-sample benchmark. Explained from zero. 04 ·Audio & Speech·★ MEMBER·PAPER·9 min read Paper Walkthrough: Interpretable MEG Decoding of Perceived Speech — Reading the Decoder's Weights as a Brain Map From three seconds of magnetoencephalography, this decoder picks the audio a listener was hearing out of 1005 candidates with 39.75% Top-1 accuracy — and, unlike its predecessors, its trained weights translate into cortical locations and rhythms, while paired occlusion experiments reveal which speech features it actually relies on.