© 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. 38441
    Prev
    Next
    INDEX
    Explanations

    references to specific, detailed statistics or data-related terms

    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
    bsolute
    -0.07
    ÙĦÛĮت
    -0.07
    emd
    -0.07
    AxisSize
    -0.07
    emoth
    -0.07
    éŀ
    -0.07
    ancellationToken
    -0.07
    olet
    -0.06
    065
    -0.06
    alse
    -0.06
    POSITIVE LOGITS
     Dexter
    0.07
    flix
    0.07
     Herald
    0.06
    ife
    0.06
    .cross
    0.06
     sinister
    0.06
    auer
    0.06
     Montgomery
    0.06
    imony
    0.06
    ?q
    0.06
    Activations Density 0.014%

    No Known Activations