Published June 19, 2026
| Version v2
Preprint
Open
Mercury Repository-to-Neuron Addressability
Description
A Mercury methods paper formalizing an address lift from code-side objects to model-side sites. The paper argues that an LLM atlas becomes more than a neuron picture when files, modules, layers, dimensions, heads, and measured sites remain linked in a testable chain. Copyright (c) 2026 Chen, Ho Yiing (norika). Licensed under Creative Commons Attribution 4.0 International (CC BY 4.0).
Notes
Author ORCID: https://orcid.org/0009-0006-6816-9891. Draft-only Zenodo record prepared for author review; not published. Mercury series artifact from the Hope of City / LLM City measurement program.
Files
mercury-repository-to-neuron-addressability-zenodo-ready.zip
Additional details
References
- Vig, Jesse. A Multiscale Visualization of Attention in the Transformer Model. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 2019. https://arxiv.org/abs/1906.05714
- Nanda, Neel; and Bloom, Joseph. TransformerLens. Software documentation, 2022. https://transformerlensorg.github.io/TransformerLens/content/citation.html
- Cooney, Alan; and Nanda, Neel. CircuitsVis. Software repository, 2023. https://github.com/TransformerLensOrg/CircuitsVis
- Elhage, Nelson; Nanda, Neel; Olsson, Catherine; Henighan, Tom; Joseph, Nicholas; Mann, Ben; Askell, Amanda; Bai, Yuntao; Chen, Anna; Conerly, Tom; DasSarma, Nova; Drain, Dawn; Ganguli, Deep; Hatfield-Dodds, Zac; Hernandez, Danny; Jones, Andy; Kernion, Jackson; Lovitt, Liane; Ndousse, Kamal; Amodei, Dario; Brown, Tom; Clark, Jack; Kaplan, Jared; McCandlish, Sam; and Olah, Chris. A Mathematical Framework for Transformer Circuits. Transformer Circuits, 2021. https://transformer-circuits.pub/2021/framework/index.html
- Carter, Shan; Armstrong, Zan; Schubert, Ludwig; Johnson, Ian; and Olah, Chris. Activation Atlas. Distill, 2019. https://distill.pub/2019/activation-atlas/