© 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. 62962
    Prev
    Next
    INDEX
    Explanations

    references to data, models, and their availability in research articles

    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
    amaz
    -0.08
    lernen
    -0.07
    adle
    -0.07
    kaar
    -0.07
    imore
    -0.07
    uz
    -0.07
    /pdf
    -0.07
    lient
    -0.07
    <typeof
    -0.07
    ãĥ«ãĥĪ
    -0.07
    POSITIVE LOGITS
     publicly
    0.08
     dataSize
    0.07
     supporting
    0.06
     repro
    0.06
     referees
    0.06
    public
    0.06
     data
    0.06
     Eg
    0.06
     freely
    0.06
    ãģıãģł
    0.06
    Activations Density 0.017%

    No Known Activations