© 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. 91715
    Prev
    Next
    INDEX
    Explanations

    phrases related to greatness or notable achievements in entertainment

    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
    /Runtime
    -0.07
    taire
    -0.07
    .Criteria
    -0.07
    онÑĮ
    -0.07
    .WinForms
    -0.07
    erken
    -0.07
    ijing
    -0.07
    ento
    -0.07
     essen
    -0.07
    positor
    -0.07
    POSITIVE LOGITS
     exist
    0.07
     Eld
    0.06
     Ang
    0.06
     existence
    0.06
     grace
    0.06
    one
    0.06
     ever
    0.06
    kova
    0.06
    kov
    0.06
     exists
    0.06
    Activations Density 0.007%

    No Known Activations