# Auxiliary Metrics Help Decoding Skill Neurons in the Wild

arXiv: https://arxiv.org/abs/2511.21610 · HTML: https://mlsanity.com/paper/2511.21610/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 15 references that are in the map.
- First posted on arXiv 26 Nov 2025.

## Builds on (most cited first, 8 of 8)

- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [Finding Neurons in a Haystack: Case Studies with Sparse Probing](https://mlsanity.com/paper/2305.01610/) (2023)
- [Learning to Generate Reviews and Discovering Sentiment](https://mlsanity.com/paper/1704.01444/) (2017)
- [Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models](https://mlsanity.com/paper/2310.17567/) (2023)

## Abstract (arXiv)

Large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, yet their internal mechanisms remain largely opaque. In this paper, we introduce a simple, lightweight, and broadly applicable method with a focus on isolating neurons that encode specific skills. Building upon prior work that identified "skill neurons" via soft prompt training on classification tasks, our approach extends the analysis to complex scenarios involving multiple skills. We correlate neuron activations with auxiliary metrics -- such as external labels and the model's own confidence score -- thereby uncovering interpretable and task-specific behaviors without the need for manual token aggregation. We empirically validate our method on tasks spanning open-ended text generation and natural language inference, demonstrating its ability to detect neurons that not only drive known skills but also reveal previously unidentified shortcuts in arithmetic reasoning on BigBench.