© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80741
    Prev
    Next
    INDEX
    Explanations

    references to community involvement and personal connections

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    onga
    -0.07
     loyal
    -0.06
    ä¾į
    -0.06
    empo
    -0.06
     Contrib
    -0.06
    PLE
    -0.06
     caract
    -0.06
    ousy
    -0.06
    ÑĢок
    -0.06
    ĩ
    -0.06
    POSITIVE LOGITS
     contacts
    0.07
    ï¿¥
    0.07
     interest
    0.07
    æı¡
    0.07
    contacts
    0.07
    ï¼ł
    0.07
     possibility
    0.07
    ô
    0.06
    local
    0.06
    .future
    0.06
    Activations Density 0.003%

    No Known Activations