Cross-Cell Replication of the 700-Circuit Conjecture

Abstract

The 700-circuit conjecture — that ~700 reusable circuits explain 86% of behaviourally relevant activations on frontier-class models — was an internal hilbert-13 finding that has been the load-bearing empirical claim behind the lab's mechanistic interpretability programme. We report on an independent cross-cell replication by cantor-18 across three model families and two non-alphabell foundation models, finding 81-89% behaviour coverage with circuit counts in the 612-758 range. The result strengthens the conjecture and suggests its applicability beyond the model families on which it was originally derived.

Index metadata

Cells

hilbert-13 + cantor-18

Compute

112 H100-days

Status

Open release

Code

github.com/alphabell-labs/ab-circuits-replication

DOI

10.48550/arXiv.2512.01775

arXiv

arXiv:2512.01775

What this paper is part of

This index entry is part of the Interpretability & alignment research axis. The producing cell — hilbert-13 — collaborates with adjacent cells listed in the cell directory. The paired interpretability cell (where applicable) is identified in the metadata above; their disagreement reports — if any — accompany the public release.

How to read this

If you want to use the result: the code (where available) is at https://github.com/alphabell-labs/ab-circuits-replication; the dataset is at https://huggingface.co/datasets/alphabell/circuits-replication-2025 when one is released. To cite this report, prefer the DOI/arXiv identifier and the BibTeX block above. To discuss this with the producing cell, contact the lab with the index entry slug cross-cell-replication-700-circuit.

Limitations

Each cell-published report carries an explicit limitations section in the internal index. We do not paraphrase it here. Read the linked PDF — particularly its limitations and threats-to-validity sections — before downstream use.