Introduces Causal Functional Signatures grounded in causal evidence and ILP-learned architectural signatures to enable explicit, comparable, and portable mechanistic claims across model scales.
The Thirteenth International Conference on Learning Representations , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 2representative citing papers
In a combinatorial toy setting, winning lottery tickets preserve families of compatible feature locations in early feature space that balance proximity to final codes with low interference, rather than specific weight subnetworks.
Language model circuits show high within-task consistency and necessity but substantial overlap across tasks, making them less specific than assumed.
Future-rhyme information is linearly decodable at line boundaries across model families and strengthens with scale, yet only Gemma-3-27B causally depends on it, with the driver migrating to the boundary around layer 30 and localizing to five attention heads.
In LLM agents, memory routing circuits emerge at 0.6B scale while content circuits appear only at 4B, and write/read operations recruit a pre-existing late-layer context hub instead of creating a new one, enabling a 76% accurate unsupervised failure diagnostic.
On-policy distillation gains efficiency from early foresight in module allocation and update directions, which the proposed EffOPD method exploits for 3x faster training with comparable performance.
citing papers explorer
-
What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis
In LLM agents, memory routing circuits emerge at 0.6B scale while content circuits appear only at 4B, and write/read operations recruit a pre-existing late-layer context hub instead of creating a new one, enabling a 76% accurate unsupervised failure diagnostic.