Model Hermeneutics: Monitoring Closed-Weight Models with Open-Weight Internals
by conti, ShivamR, Jacob Sharf, jain18ayush, and johnyan
We introduce model hermeneutics: studying a closed-weight model (the author model) through the internals of an open-weight substitute (the reader model). We find: 1. Weak to strong readers can work. A 27B reader was able to match the performance of probing a 397B author. 2. Probes on open-weight reader models...
Sep 3017