© 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. 1156
    Prev
    Next
    INDEX
    Explanations

    detailed accounts of sports activities and player performances

    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
    _ASSUME
    -0.07
    BUFF
    -0.06
    boo
    -0.06
    anno
    -0.06
    ä¸ļ
    -0.06
     služ
    -0.06
     trat
    -0.06
    unci
    -0.06
    tones
    -0.06
    売
    -0.06
    POSITIVE LOGITS
    .advance
    0.07
    lesen
    0.07
     progress
    0.06
     private
    0.06
     Rebellion
    0.06
    isol
    0.06
    /Private
    0.06
    wend
    0.06
     dou
    0.06
    à¥ĩस
    0.06
    Activations Density 0.015%

    No Known Activations