© 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. 87576
    Prev
    Next
    INDEX
    Explanations

    references to notable sports players and their achievements

    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
    ibold
    -0.08
    .Automation
    -0.08
    oge
    -0.07
    ÑĤеÑĢи
    -0.07
    alendar
    -0.07
    afen
    -0.07
    uess
    -0.07
    unner
    -0.07
    FML
    -0.07
    igos
    -0.07
    POSITIVE LOGITS
     figure
    0.08
    owitz
    0.07
    æŃ´
    0.07
    -figure
    0.07
     history
    0.06
     Greatest
    0.06
     era
    0.06
     generation
    0.06
    /browse
    0.06
    history
    0.06
    Activations Density 0.025%

    No Known Activations