# Subliminal Steering: Stronger Encoding of Hidden Signals

arXiv: https://arxiv.org/abs/2604.25783 · HTML: https://mlsanity.com/paper/2604.25783/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 18 of its 23 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Placed in

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

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

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://mlsanity.com/paper/2502.17424/) (2025)
- [Breaking the Softmax Bottleneck: A High-Rank RNN Language Model](https://mlsanity.com/paper/1711.03953/) (2017)
- [Subliminal Learning: Language models transmit behavioral traits via hidden signals in data](https://mlsanity.com/paper/2507.14805/) (2025)
- [SelfIE: Self-Interpretation of Large Language Model Embeddings](https://mlsanity.com/paper/2403.10949/) (2024)
- [LatentQA: Teaching LLMs to Decode Activations Into Natural Language](https://mlsanity.com/paper/2412.08686/) (2024)
- [Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer](https://mlsanity.com/paper/2509.23886/) (2025)
- [Closing the Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/2310.01693/) (2023)
- [One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs](https://mlsanity.com/paper/2502.18862/) (2025)
- [Emergent Misalignment is Easy, Narrow Misalignment is Hard](https://mlsanity.com/paper/2602.07852/) (2026)
- [From Data to Behavior: Predicting Unintended Model Behaviors Before Training](https://mlsanity.com/paper/2602.04735/) (2026)
- [Synthetic Data for any Differentiable Target](https://mlsanity.com/paper/2604.08423/) (2026)

## Built on by (most cited first, 14 of 14)

- [Subliminal Learning Is Steering Vector Distillation](https://mlsanity.com/paper/2606.00995/) (2026)
- [Learning Through Noise: Why Subliminal Learning Works and When It Fails](https://mlsanity.com/paper/2605.23645/) (2026)
- [Subliminal Learning is a LoRA Artifact](https://mlsanity.com/paper/2606.00831/) (2026)
- [Stored in Optimizer State, Valued by Later Training: A Causal Account of Subliminal Trait Transfer](https://mlsanity.com/paper/2608.20442/) (2026)
- [Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust](https://mlsanity.com/paper/2607.00083/) (2026)
- [Subliminal Prompting Beyond Static Geometry: Causal Depth and Multi-Token Confounds](https://mlsanity.com/paper/2609.19149/) (2026)
- [Can Data Attribution Filter Out Subliminal Learning? Not Reliably](https://mlsanity.com/paper/2609.20027/) (2026)
- [On Mitigation of Subliminal Learning in Large Language Models](https://mlsanity.com/paper/2609.22215/) (2026)
- [Why Ghost Outputs Teach: A Kernel-Based Understanding of Subliminal Learning](https://mlsanity.com/paper/2609.23260/) (2026)
- [Cross-Trait Transfer in Subliminal Learning](https://mlsanity.com/paper/2610.04260/) (2026)
- [Why Subliminal Learning Needs So Much Data: A Noisy Inverse View through Steering Vector Recovery](https://mlsanity.com/paper/2610.04907/) (2026)
- [Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors](https://mlsanity.com/paper/2610.10657/) (2026)
- [Defence against the dark arts of distillation: Unsupervised discovery of subliminal learning](https://mlsanity.com/paper/2610.13536/) (2026)
- [Imprinting: Knowledge Distillation Can Shift Student Behavior](https://mlsanity.com/paper/2610.18517/) (2026)

## Abstract (arXiv)

Subliminal learning describes a student language model inheriting a behavioral bias by fine-tuning on seemingly innocuous data generated by a biased teacher model. Prior work has begun to characterize this phenomenon but leaves open questions about the scope of signals it can transfer, the mechanisms that explain it, and the precision with which a bias can be encoded. We tackle these problems by introducing subliminal steering, a variant of subliminal learning in which the teacher's bias is implemented not via a system prompt, as in prior work, but through a steering vector trained to maximize the likelihood of a set of target samples. First, we show that subliminal steering transfers complex multi-word biases, whereas prior work focused on single-word preferences, demonstrating a large scope of subliminally transferable signals. Moreover, the transfer is reliable enough to appear in settings previously thought not to exhibit subliminal learning, including plain SGD (not just Adam), full fine-tuning (not just LoRA), and models such as Llama and Phi. Second, we provide mechanistic evidence that subliminal learning transfers not only the target behavioral bias, but also the steering vector itself, localized to the layers at which the teacher was steered. Finally, we show that the bias is encoded with such precision that a new steering vector trained on the subliminally-laden dataset attains high cosine similarity with the original vector.