© 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. 42557
    Prev
    Next
    INDEX
    Explanations

    header tags of various levels in HTML documents

    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
    assium
    -0.07
    ayd
    -0.07
    ngine
    -0.07
    .sharedInstance
    -0.07
    egan
    -0.06
    ay
    -0.06
    боÑĤ
    -0.06
    ugh
    -0.06
    bsolute
    -0.06
     Lah
    -0.06
    POSITIVE LOGITS
    oret
    0.07
    MLE
    0.07
    ories
    0.06
     Lester
    0.06
    stan
    0.06
    ith
    0.06
    STALL
    0.06
    à¥Īल
    0.06
    aven
    0.06
    -font
    0.06
    Activations Density 0.003%

    No Known Activations