# Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts

arXiv: https://arxiv.org/abs/2501.02009 · HTML: https://mlsanity.com/paper/2501.02009/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jan 2025.

## Built on by (most cited first, 12 of 12)

- [Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse](https://mlsanity.com/paper/2608.03893/) (2026)
- [From Data to Behavior: Predicting Unintended Model Behaviors Before Training](https://mlsanity.com/paper/2602.04735/) (2026)
- [Steer-MoE: Efficient Audio-Language Alignment with a Mixture-of-Experts Steering Module](https://mlsanity.com/paper/2510.13558/) (2025)
- [Atlas-Alignment: Making Interpretability Transferable Across Language Models](https://mlsanity.com/paper/2510.27413/) (2025)
- [Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes](https://mlsanity.com/paper/2608.05000/) (2026)
- [Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation](https://mlsanity.com/paper/2606.05290/) (2026)
- [The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment](https://mlsanity.com/paper/2604.06377/) (2026)
- [Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering](https://mlsanity.com/paper/2604.12210/) (2026)
- [HyperTransport: Amortized Conditioning of T2I Generative Models](https://mlsanity.com/paper/2605.08254/) (2026)
- [Contrastive-Difference CKA Reveals Concept-Specific Structural Alignment Across Language Model Architectures](https://mlsanity.com/paper/2606.16897/) (2026)
- [Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents](https://mlsanity.com/paper/2608.18351/) (2026)
- [Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts](https://mlsanity.com/paper/2610.20067/) (2026)

## Abstract (arXiv)

Understanding the inner workings of Large Language Models (LLMs) is a critical research frontier. Prior research has shown that a single LLM's concept representations can be captured as steering vectors (SVs), enabling the control of LLM behavior (e.g., towards generating harmful content). Our work takes a novel approach by exploring the intricate relationships between concept representations across different LLMs, drawing an intriguing parallel to Plato's Allegory of the Cave. In particular, we introduce a linear transformation method to bridge these representations and present three key findings: 1) Concept representations across different LLMs can be effectively aligned using simple linear transformations, enabling efficient cross-model transfer and behavioral control via SVs. 2) This linear transformation generalizes across concepts, facilitating alignment and control of SVs representing different concepts across LLMs. 3) A weak-to-strong transferability exists between LLM concept representations, whereby SVs extracted from smaller LLMs can effectively control the behavior of larger LLMs.