# Inverted Detection and Control in Steering Vectors

arXiv: https://arxiv.org/abs/2608.02957 · HTML: https://mlsanity.com/paper/2608.02957/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 33 of its 42 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Placed in

- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [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)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Function Vectors in Large Language Models](https://mlsanity.com/paper/2310.15213/) (2023)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [ReFT: Representation Finetuning for Language Models](https://mlsanity.com/paper/2404.03592/) (2024)
- [Open Problems in Mechanistic Interpretability](https://mlsanity.com/paper/2501.16496/) (2025)
- [Analyzing the Generalization and Reliability of Steering Vectors](https://mlsanity.com/paper/2407.12404/) (2024)
- [Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization](https://mlsanity.com/paper/2406.00045/) (2024)
- [The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models](https://mlsanity.com/paper/2601.10387/) (2026)
- [Controlling Language and Diffusion Models by Transporting Activations](https://mlsanity.com/paper/2410.23054/) (2024)
- [LoFiT: Localized Fine-tuning on LLM Representations](https://mlsanity.com/paper/2406.01563/) (2024)
- [Spectral Editing of Activations for Large Language Model Alignment](https://mlsanity.com/paper/2405.09719/) (2024)
- [Understanding (Un)Reliability of Steering Vectors in Language Models](https://mlsanity.com/paper/2505.22637/) (2025)
- [A Unified Understanding and Evaluation of Steering Methods](https://mlsanity.com/paper/2502.02716/) (2025)
- [Who's asking? User personas and the mechanics of latent misalignment](https://mlsanity.com/paper/2406.12094/) (2024)
- [Relational Composition in Neural Networks: A Survey and Call to Action](https://mlsanity.com/paper/2407.14662/) (2024)
- [Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models](https://mlsanity.com/paper/2508.10599/) (2025)
- [Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models](https://mlsanity.com/paper/2602.01654/) (2026)
- [RepIt: Steering Language Models with Concept-Specific Refusal Vectors](https://mlsanity.com/paper/2509.13281/) (2025)
- [CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering](https://mlsanity.com/paper/2602.03420/) (2026)

## Abstract (arXiv)

Steering vectors (SVs) are widely used to influence the expression of concepts (e.g., truthfulness) in large language model outputs. A key assumption underpinning SVs is that they are linearly discriminative with respect to the concept: representations of texts that exhibit the concept are more aligned with the SV than those that do not, motivating shifts along the positive or negative SV direction to respectively promote or suppress the concept. In this work, we identify an inverted detection-control phenomenon in which some highly discriminative SVs that are aligned with positive representations can consistently promote the opposite behavior. We refer to such vectors as inverted-steering vectors (ISVs). We provide a geometric characterization of ISVs' effects, finding that steering along these directions systematically pushes representations in discriminative downstream heads as if the concept were absent, even prior to decoding. Motivated by this analysis, we propose an approach for distinguishing ISVs without requiring generation or associated response scoring. This enables targeted sign flips, which we use to improve a foundational detection-based steering pipeline via Inference Time Intervention (ITI). Our approach improves results in 27/30 experiments, ranging from +0.9% to +138%. We evaluate our findings on Gemma 3 12B, Qwen 2.5 14B, and Olmo 3 7B across 5 concepts.