© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128078
    Prev
    Next
    INDEX
    Explanations

    events related to crime or police activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enos
    -0.08
     ifndef
    -0.07
    aeda
    -0.07
    ırak
    -0.07
    antar
    -0.07
     Berm
    -0.07
    _contrib
    -0.07
     newcom
    -0.07
    ylko
    -0.07
    enant
    -0.07
    POSITIVE LOGITS
     chase
    0.08
     running
    0.07
     police
    0.07
    Dash
    0.06
     turns
    0.06
     End
    0.06
     pursuit
    0.06
     law
    0.06
    running
    0.06
    0.06
    Activations Density 0.002%

    No Known Activations