# The Signs Were Always There: Training-Free Concept Detection and Steering in Raw Transformer Dimensions

arXiv: https://arxiv.org/abs/2606.12629 · HTML: https://mlsanity.com/paper/2606.12629/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 18 of 18)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet](https://mlsanity.com/paper/2605.29358/) (2026)
- [Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks](https://mlsanity.com/paper/1801.03454/) (2018)
- [Steering CLIP's vision transformer with sparse autoencoders](https://mlsanity.com/paper/2504.08729/) (2025)
- [Learning Interpretable Features in Audio Latent Spaces via Sparse Autoencoders](https://mlsanity.com/paper/2510.23802/) (2025)

## Abstract (arXiv)

The standard basis of transformer hidden states is a training-free, architecture-general feature basis for detecting concepts and, in language models, steering them; with no learned dictionary. Individual dimensions act as binary registers read one at a time: their signs (+/-1) encode content, their magnitudes strength. A feature is just a subset of dimensions with a consistent sign pattern, read by counting sign agreements. We validate this Bag of Dims (BoD) framework across seven models spanning language, vision, and audio; reading dimensions one at a time loses nothing, as a full-capacity MLP adds zero AUC over per-dim reading. The same per-dimension signs appear in every modality, so they reflect transformer training itself, not the language objective. Sign alone carries predictive content: setting all magnitudes to unity preserves 60-93% top-5 next-token accuracy through the LM head. From a single-token cache (one forward pass per token, no labels) we detect 175 categories at AUC 0.97-0.99 by counting sign agreements, and from random seeds alone discovery scales to 1500 features per model. A trained probe adds only +0.018 AUC and converges to axis-aligned weights: the rotation dictionaries learn buys little. Signs are causally operative: they survive the attention projections, and flipping a concept's sign pattern in the live forward pass suppresses it. Reading and steering are separate roles in the same basis: a concept's reader dimensions are not its writer dimensions. The writer target is just as cheap, the sign of the summed unembedding rows over a few seeds, no training. Injected through the attention output pathway under closed-loop control, it steers concepts into fluent text on four language models (62-92% of twelve concepts). The signs were in the standard basis all along; the open problem is no longer finding the right rotation but cataloging what each dimension encodes.