Research

SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise

Single source1 source14 Oct 2026

arXiv:2610.17093v1 Announce Type: new Abstract: A model diff credits post-training with whatever separates a base checkpoint from one post-trained descendant, presuming a rerun would land close by.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.17093

← Back to all developments · Signals are a development reported by more than one source. See the methodology.