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

    Neuronpedia

    Jacobian LensNEW
    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. 58882
    Prev
    Next
    INDEX
    Explanations

    references to sports events and athletes

    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
     tongues
    -0.07
    edback
    -0.07
    lier
    -0.07
    mpar
    -0.06
    uchar
    -0.06
    SSION
    -0.06
    ÑĥÑĩа
    -0.06
    ason
    -0.06
    PAIR
    -0.06
     punt
    -0.06
    POSITIVE LOGITS
    gow
    0.07
    obo
    0.07
     Parcel
    0.06
    _CAST
    0.06
     Robbins
    0.05
    islav
    0.05
    MES
    0.05
    departments
    0.05
     cerv
    0.05
     ausge
    0.05
    Activations Density 0.003%

    No Known Activations