Sky sphere representation in language models
Mirrored from arXiv — Machine Learning for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
Title:Sky sphere representation in language models
Abstract:We analyze whether language models of size ~100B have a representation of the night sky map that is decodable from their residual stream. We find that most of the considered open-source models do have such a representation, and it often even surfaces to the top principal components on prompts that ask questions like ``what is close to this object in the night sky''. In all but one model this representation showed significant scores in LOO testing, containing up to 65-85% of variance ($R^2$-score) and having median angular error down to $12^\circ-21^\circ$. We verify that our representation is not a simple leak from a correlated flat representation. To our knowledge, this representation is the first example of a curved high-dimensional irreducible feature manifold.
Codes used in the paper are published at this https URL
| Subjects: | Machine Learning (cs.LG) |
| MSC classes: | 68T30 |
| ACM classes: | I.2.4 |
| Cite as: | arXiv:2607.27092 [cs.LG] |
| (or arXiv:2607.27092v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2607.27092
arXiv-issued DOI via DataCite (pending registration)
|
Submission history
From: Aleksandr Berdnikov [view email][v1] Wed, 29 Jul 2026 16:19:43 UTC (3,108 KB)
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
References & Citations
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — Machine Learning
-
Learning Discrete Riemannian Metrics for Physical Fields with Cochain-Frame Equivarianc
Aug 18
-
Forward Pass Domain Adaptation (Without Cross-Layer Backpropagation)
Aug 18
-
Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems
Aug 18
-
Geometry Is Not Robustness: A Trajectory-Level Study of PGD Evaluation
Aug 18
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.