Ghost Tracks: Hypothesis Competition in Sparse Feature Space as a Preliminary Signal of LLM Hallucinations

Large language models frequently suffer from hallucinations, generating text that is fluent but factually incorrect. While empirical detection methods exist, the underlying internal mechanisms and representation dynamics that cause models to hallucinate remain poorly understood. In this work, we present preliminary evidence that hallucinations are associated with a failure to resolve competing semantic hypotheses within the model's residual stream. Specifically, by linking Sparse Autoencoder (SAE) features across layers with a multi-hypothesis tracker, we observe that factual outputs tend to correspond to a single dominating feature, while hallucinations exhibit "ghost tracks"---multiple semantic candidates that transiently activate and compete without a clear winner. Leveraging this observation, we propose GhostTrack, a detector that extracts feature-competition metrics from a single forward pass and reaches up to 0.903 AUROC on Phi-2 (0.722 on GPT-2 Medium, 0.650 on Qwen2.5-1.5B) on the HaluEval QA benchmark. We further analyze these dynamics to show that feature entropy and dominance margins are the strongest signals of competition failure, with class separation most pronounced in the middle-to-late transformer layers. Our findings provide correlational, interpretable evidence that hallucinations coincide with measurable failures of internal representation resolution. More broadly, our work lays the groundwork for causal interventions that monitor and steer feature dynamics during inference to improve the factual reliability of AI systems.