cd /news/large-language-models/sky-sphere-representation-in-languag… · home topics large-language-models article
[ARTICLE · art-126427] src=arxiv.org ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Sky sphere representation in language models (29 Jul 2026)

A 29 July 2026 arXiv paper by Aleksandr Berdnikov reports that most open-source language models of roughly 100B parameters hold a decodable representation of the night sky map in their residual stream, with the representation surfacing to top principal components on prompts such as "what is close to this object in the night sky." In all but one model the representation scored significantly in leave-one-out testing, capturing 65-85% of variance (R²-score) with median angular error as low as 12°-21°. The authors state this is the first example of a curved high-dimensional irreducible feature manifold, and published the code at github.com/l3erdnik/Decodable-sky.

read2 min views1 publishedSep 11, 2026
Sky sphere representation in language models (29 Jul 2026)
Image: source
  [Submitted on 29 Jul 2026]


[View PDF](/pdf/2607.27092)

[HTML (experimental)](https://arxiv.org/html/2607.27092v1)

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 atthis https URL

Submission history #

From: Aleksandr Berdnikov [
[view email](/show-email/71e4ac5c/2607.27092)]

**[v1]** Wed, 29 Jul 2026 16:19:43 UTC (3,108 KB)

References & Citations

...

Bibliographic Explorer

(What is the Explorer?) Connected Papers

(What is Connected Papers?) Litmaps

(What is Litmaps?) scite Smart Citations

(What are Smart Citations?) alphaXiv

(What is alphaXiv?) CatalyzeX Code Finder for Papers

(What is CatalyzeX?) DagsHub

(What is DagsHub?) Gotit.pub

(What is GotitPub?) Hugging Face

(What is Huggingface?) ScienceCast

(What is ScienceCast?) Influence Flower

(What are Influence Flowers?) CORE Recommender

(What is CORE?) IArxiv Recommender

(What is IArxiv?) 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 in #large-language-models 4 stories · sorted by recency
── more on @aleksandr berdnikov 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/sky-sphere-represent…] indexed:0 read:2min 2026-09-11 ·