© 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. 76450
    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
    PROTO
    -0.07
    ockey
    -0.07
    Ìģ
    -0.06
    onth
    -0.06
    Ø®ÙĪاÙĨ
    -0.06
    OND
    -0.06
    Å¡k
    -0.06
    keley
    -0.06
    sterol
    -0.06
    uania
    -0.06
    POSITIVE LOGITS
    วย
    0.07
    adaki
    0.06
    ASA
    0.06
    ëĿ½
    0.06
    _fre
    0.06
     <<<
    0.06
    .btnExit
    0.06
    械
    0.06
     flash
    0.06
    Ñģен
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.