High-dimensional layer-state trajectories reveal the internal dynamics of transformer inference
arXiv:2610.26866v1 Announce Type: new Abstract: Mechanistic studies of large language models localize function in parameters, attention heads or neurons, but those parts do not specify how one inference unfolds. We treat the ordered layer-state trajectory as the empirical process and test whether l…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-21 04:00 · arXiv cs.LG
High-dimensional layer-state trajectories reveal the internal dynamics of transformer inference