© 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. 58300
    Prev
    Next
    INDEX
    Explanations

    references to female artists and the representation of women in comics

    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
    607
    -0.06
    /bind
    -0.06
    rale
    -0.06
    ninger
    -0.06
     cine
    -0.06
    606
    -0.06
    884
    -0.06
    gal
    -0.06
    cheid
    -0.06
     Fus
    -0.06
    POSITIVE LOGITS
     approach
    0.07
    Except
    0.07
     affair
    0.07
    senal
    0.06
    _Impl
    0.06
    ¶Į
    0.06
    ÑĮв
    0.06
    -ни
    0.06
     entirely
    0.06
     except
    0.06
    Activations Density 0.019%

    No Known Activations