Know a great AI tool or AI news source? Submit it to AiByts
2 min read

Spokes, not a Ring: Revisiting the Weekday Manifold in Language Models

Recent work has hypothesised that large language models may represent some concepts as multi-dimensional manifolds instead of single directions. Using these manifolds to interpret or steer representations often assumes that moving along them corresponds to a continuous change in the represented…

By Diksha Gupta, Rieke Fruengel, Stefan HeimersheimarXiv cs.LG

Read the full story

Originally published by arXiv cs.LG on Oct 30, 2026.

Read on arXiv cs.LG(opens in a new tab)

Comments

Sign in to join the discussion.

No comments yet — be the first to share your thoughts.