© 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. 54982
    Prev
    Next
    INDEX
    Explanations

    mentions of professional football players and their performance metrics

    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
    ubi
    -0.07
    roys
    -0.07
     Democracy
    -0.07
     Rat
    -0.06
    imoto
    -0.06
     Punch
    -0.06
    _rat
    -0.06
     поÑħ
    -0.06
     TMPro
    -0.06
    /uploads
    -0.06
    POSITIVE LOGITS
     draft
    0.10
     selections
    0.10
     drafting
    0.10
    draft
    0.09
     pick
    0.09
     drafted
    0.09
     picks
    0.09
    -selection
    0.09
     Draft
    0.09
     дÑĢа
    0.08
    Activations Density 0.152%

    No Known Activations