© 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. 63267
    Prev
    Next
    INDEX
    Explanations

    references to personal or financial details about individuals

    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
    ouden
    -0.07
    lopedia
    -0.07
    uchar
    -0.06
    vak
    -0.06
    idar
    -0.06
     Provincial
    -0.06
    ruba
    -0.06
    iche
    -0.06
    indow
    -0.06
    paque
    -0.06
    POSITIVE LOGITS
     NÄĽkterá
    0.07
    Reporting
    0.07
    ixo
    0.07
    ÎĻΣ
    0.07
    ÛĢ
    0.06
    .Reporting
    0.06
    zano
    0.06
    ìĪĺ
    0.06
    .RELATED
    0.06
     ìĽ¹ìĤ¬ìĿ´íĬ¸
    0.06
    Activations Density 0.001%

    No Known Activations