© 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. 121308
    Prev
    Next
    INDEX
    Explanations

    references to political leaders and their titles

    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
     bruk
    -0.07
    ỳ
    -0.06
    Æ°á»
    -0.06
    Ìī
    -0.06
     Decimal
    -0.06
     Mile
    -0.06
    ÄĽst
    -0.06
    ï¼ĮåŃĺäºİ
    -0.06
    /*č↵
    -0.06
    Ã¼ÅŁ
    -0.06
    POSITIVE LOGITS
     said
    0.07
    æ°ı
    0.06
    çµ
    0.06
    Also
    0.06
     also
    0.06
     ALSO
    0.06
    ä¹ĭ
    0.06
     kıs
    0.06
    .indent
    0.06
    ç´
    0.06
    Activations Density 0.013%

    No Known Activations