# Toward universal steering and monitoring of AI models

arXiv: https://arxiv.org/abs/2502.03708 · HTML: https://mlsanity.com/paper/2502.03708/

## Key facts

- Cited by 29 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 6 Feb 2025.

## Built on by (most cited first, 29 of 29)

- [Representation Engineering for Large-Language Models: Survey and Research Challenges](https://mlsanity.com/paper/2502.17601/) (2025)
- [xRFM: Accurate, scalable, and interpretable feature learning models for tabular data](https://mlsanity.com/paper/2508.10053/) (2025)
- [Linear Personality Probing and Steering in LLMs: A Big Five Study](https://mlsanity.com/paper/2512.17639/) (2025)
- [Efficient and accurate steering of Large Language Models through attention-guided feature learning](https://mlsanity.com/paper/2602.00333/) (2026)
- [Resa: Transparent Reasoning Models via SAEs](https://mlsanity.com/paper/2506.09967/) (2025)
- [Steering Autoregressive Music Generation with Recursive Feature Machines](https://mlsanity.com/paper/2510.19127/) (2025)
- [From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents](https://mlsanity.com/paper/2604.19775/) (2026)
- [The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks](https://mlsanity.com/paper/2605.06258/) (2026)
- [Reasoning-Intensive Regression](https://mlsanity.com/paper/2508.21762/) (2025)
- [Steerability of Instrumental-Convergence Tendencies in LLMs](https://mlsanity.com/paper/2601.01584/) (2026)
- [SHIFT: Steering Hidden Intermediates in Flow Transformers](https://mlsanity.com/paper/2604.09213/) (2026)
- [HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces](https://mlsanity.com/paper/2604.19001/) (2026)
- [The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge](https://mlsanity.com/paper/2605.12908/) (2026)
- [Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models](https://mlsanity.com/paper/2602.07794/) (2026)
- [General and Efficient Steering of Diffusion Models](https://mlsanity.com/paper/2602.11395/) (2026)
- [As Language Models Scale, Low-order Linear Depth Dynamics Emerge](https://mlsanity.com/paper/2603.12541/) (2026)
- [Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs](https://mlsanity.com/paper/2604.08846/) (2026)
- [Breaking Bad: Interpretability-Based Safety Audits of State-of-the-Art LLMs](https://mlsanity.com/paper/2604.20945/) (2026)
- [A Universal Space of Brain Dynamics for Unveiling Cognitive Transitions and Individual Differences](https://mlsanity.com/paper/2605.02936/) (2026)
- [Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts](https://mlsanity.com/paper/2605.12890/) (2026)
- [Steered Generation via Gradient-Based Optimization on Sparse Query Features](https://mlsanity.com/paper/2605.23040/) (2026)
- [Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection](https://mlsanity.com/paper/2605.28664/) (2026)
- [Validation-Gated Causal Interventions for Interpreting High-Stakes Large Language Model Behavior: A Case Study in Suicidality Detection](https://mlsanity.com/paper/2606.21078/) (2026)
- [Distributed Sparse Interventions in Language Models](https://mlsanity.com/paper/2607.07128/) (2026)
- [Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift](https://mlsanity.com/paper/2607.17524/) (2026)
- [RepBench: Compiling Benchmarks into Capability Representations for Large Language Models](https://mlsanity.com/paper/2607.28008/) (2026)
- [Measuring Concept Content in Text from LLM Activations: ESG Evidence from Concept Vectors and Linear Probes](https://mlsanity.com/paper/2608.07208/) (2026)
- [Refusal geometry reflects refusal training: diverse refusal prefixes can raise stable rank and weaken refusal vector ablation attacks](https://mlsanity.com/paper/2608.25390/) (2026)
- [MASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language Models](https://mlsanity.com/paper/2609.39107/) (2026)

## Abstract (arXiv)

Modern AI models contain much of human knowledge, yet understanding of their internal representation of this knowledge remains elusive. Characterizing the structure and properties of this representation will lead to improvements in model capabilities and development of effective safeguards. Building on recent advances in feature learning, we develop an effective, scalable approach for extracting linear representations of general concepts in large-scale AI models (language models, vision-language models, and reasoning models). We show how these representations enable model steering, through which we expose vulnerabilities, mitigate misaligned behaviors, and improve model capabilities. Additionally, we demonstrate that concept representations are remarkably transferable across human languages and combinable to enable multi-concept steering. Through quantitative analysis across hundreds of concepts, we find that newer, larger models are more steerable and steering can improve model capabilities beyond standard prompting. We show how concept representations are effective for monitoring misaligned content (hallucinations, toxic content). We demonstrate that predictive models built using concept representations are more accurate for monitoring misaligned content than using models that judge outputs directly. Together, our results illustrate the power of using internal representations to map the knowledge in AI models, advance AI safety, and improve model capabilities.