# Subliminal Learning is Non-Semantic Distillation

arXiv: https://arxiv.org/abs/2608.05734 · HTML: https://mlsanity.com/paper/2608.05734/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Placed in

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

## Builds on (most cited first, 15 of 15)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Linear Mode Connectivity and the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1912.05671/) (2019)
- [Exponential expressivity in deep neural networks through transient chaos](https://mlsanity.com/paper/1606.05340/) (2016)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [Subliminal Learning: Language models transmit behavioral traits via hidden signals in data](https://mlsanity.com/paper/2507.14805/) (2025)
- [Improving Activation Steering in Language Models with Mean-Centring](https://mlsanity.com/paper/2312.03813/) (2023)
- [Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs](https://mlsanity.com/paper/2512.09742/) (2025)
- [Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning](https://mlsanity.com/paper/2504.02922/) (2025)
- [Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer](https://mlsanity.com/paper/2509.23886/) (2025)
- [Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences](https://mlsanity.com/paper/2510.13900/) (2025)
- [Simple Mechanistic Explanations for Out-Of-Context Reasoning](https://mlsanity.com/paper/2507.08218/) (2025)

## Built on by (most cited first, 3 of 3)

- [Post-Training Leaves Behavioral Shadows on Unrelated Decisions](https://mlsanity.com/paper/2609.29233/) (2026)
- [Cross-Trait Transfer in Subliminal Learning](https://mlsanity.com/paper/2610.04260/) (2026)
- [Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors](https://mlsanity.com/paper/2610.10657/) (2026)

## Abstract (arXiv)

Subliminal Learning (SL) is a surprising type of generalization displayed by modern language models. It allows the transfer of a bias or behavior from a teacher model to a student by distilling from seemingly unrelated or random synthetic data from the teacher. This presents challenges in ensuring AI systems remain predictable and are trained safely, as standard auditing of the input data would not catch the hidden subliminal signal. Here, we investigate several open questions as to the enabling mechanisms and drivers of SL. First is the nature of the process by which biases are encoded in the data. We find that by adding Gaussian noise to the weights of the teacher and student models, the magnitude of subliminal transfer is increased by a factor of 1.9 in Gemma and 1.3 in Llama, suggesting that non-semantic weight structures play a crucial role. We show that steering vectors can be applied to the teacher to produce subliminal data, in addition to prompting and finetuning as used in previous studies. Analysis of the activations of the student models that have been trained on steered and prompted data demonstrates that students inherit not just the semantic meaning of the teacher's bias, but also the type of intervention that was used to apply it: steered students imitate steering vectors, prompted students do not. Additionally, the gradients of steered subliminal data show a linear correlation with the teacher's steering vectors, showing promise for data auditing. More broadly, as synthetic data becomes central to frontier training pipelines, being able to see the latent signals hidden in training data becomes paramount.