Automated Attention Pattern Discovery at Scale in Large Language Models
Large language models have found success by scaling up capabilities to work in general settings. The same can unfortunately not be said for interpretability methods. The current trend in mechanistic interpretability is to provide precise explanations of specific behaviors in controlled settings. These often do not generalize, or are too resource intensive for larger studies. In this work we propose to study repeated behaviors in large language models by mining completion scenarios in Java code datasets, through exploiting the structured nature of code. We collect the attention patterns generated in the attention heads to demonstrate that they are scalable signals for global interpretabili...
| Authors | Jonathan Katzy, Razvan-Mihai Popescu, Erik Mekkes et al. |
|---|---|
| Primary category | cs.LG |
| Published | 4 April 2026 |
| Last updated at source | 4 April 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.