{"slug": "sky-sphere-representation-in-language-models-29-jul-2026", "title": "Sky sphere representation in language models (29 Jul 2026)", "summary": "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.", "body_md": "# Computer Science > Machine Learning\n\n  [Submitted on 29 Jul 2026]\n\n# Title:Sky sphere representation in language models\n\n[View PDF](/pdf/2607.27092)\n\n[HTML (experimental)](https://arxiv.org/html/2607.27092v1)\n\nAbstract: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.\n\nCodes used in the paper are published at[this https URL](https://github.com/l3erdnik/Decodable-sky)\n\n## Submission history\n\nFrom: Aleksandr Berdnikov [\n[view email](/show-email/71e4ac5c/2607.27092)]\n\n**[v1]** Wed, 29 Jul 2026 16:19:43 UTC (3,108 KB)\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/sky-sphere-representation-in-language-models-29-jul-2026", "canonical_source": "https://arxiv.org/abs/2607.27092", "published_at": "2026-09-11 01:22:50+00:00", "updated_at": "2026-09-11 01:53:29.200146+00:00", "lang": "en", "topics": ["large-language-models", "machine-learning", "ai-research", "artificial-intelligence"], "entities": ["Aleksandr Berdnikov", "arXiv", "Decodable-sky"], "alternates": {"html": "https://wpnews.pro/news/sky-sphere-representation-in-language-models-29-jul-2026", "markdown": "https://wpnews.pro/news/sky-sphere-representation-in-language-models-29-jul-2026.md", "text": "https://wpnews.pro/news/sky-sphere-representation-in-language-models-29-jul-2026.txt", "jsonld": "https://wpnews.pro/news/sky-sphere-representation-in-language-models-29-jul-2026.jsonld"}}