© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16407
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ieber
    -0.06
     Mec
    -0.06
    adt
    -0.06
     suf
    -0.06
     Tow
    -0.06
    strup
    -0.06
    ingu
    -0.06
    406
    -0.06
     spots
    -0.06
    onaut
    -0.06
    POSITIVE LOGITS
    oyo
    0.07
     Sens
    0.07
    leen
    0.07
    orda
    0.06
     Ded
    0.06
    aram
    0.06
    jak
    0.06
    енÑģ
    0.06
    _attach
    0.06
    .Constraint
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.