# Deep Learning Models Also Recall Features

arXiv: https://arxiv.org/abs/2608.20970 · HTML: https://mlsanity.com/paper/2608.20970/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Circuits and mechanistic analysis, one of 13 directions in Mechanistic interpretability.
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Placed in

- Mechanistic interpretability / [Circuits and mechanistic analysis](https://mlsanity.com/mechinterp/circuits-and-mechanistic-analysis/)

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

- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet](https://mlsanity.com/paper/2605.29358/) (2026)
- [Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs](https://mlsanity.com/paper/2402.07321/) (2024)
- [Standards for Belief Representations in LLMs](https://mlsanity.com/paper/2405.21030/) (2024)
- [How Do LLMs Use Their Depth?](https://mlsanity.com/paper/2510.18871/) (2025)
- [Mechanistic Indicators of Understanding in Large Language Models](https://mlsanity.com/paper/2507.08017/) (2025)
- [Mechanistic Interpretability Needs Philosophy](https://mlsanity.com/paper/2506.18852/) (2025)

## Abstract (arXiv)

Recent work in mechanistic interpretability has studied how large language models recall facts stored in their weights. This paper argues that factual recall points to something broader: a general kind of operation in deep learning models, which I call feature recall. The core observation is that a linear projection can be read as retrieving stored information scaled by input activations. I define feature recall, show it applies across architectures, and contrast it with the established paradigm of feature combination. I also consider how cases of feature recall might be mechanistically identified. The account gives philosophers a new conceptual tool for understanding deep learning, and points to empirical directions for mechanistic interpretability research.