© 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 EvalsExportsinterp-engineNEWAPI 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. 42271
    Prev
    Next
    INDEX
    Explanations

    terms related to player roles and positions in sports

    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
    erli
    -0.09
    avanaugh
    -0.08
    urga
    -0.07
    gil
    -0.07
    stretch
    -0.07
    iset
    -0.07
     porr
    -0.07
    ÑĥÑĩа
    -0.07
    agli
    -0.07
    PÅĻed
    -0.07
    POSITIVE LOGITS
    -only
    0.07
    rous
    0.06
    mas
    0.06
     Hell
    0.06
     mode
    0.06
    /back
    0.06
    MAS
    0.06
    599
    0.06
    iling
    0.06
     position
    0.06
    Activations Density 0.030%

    No Known Activations