© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 5255
    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
    ilenames
    -0.06
    rak
    -0.06
    normally
    -0.06
    kus
    -0.06
    USES
    -0.06
    اÙĩÙħ
    -0.06
    roi
    -0.05
    PEND
    -0.05
     cre
    -0.05
    .BorderFactory
    -0.05
    POSITIVE LOGITS
     ongoing
    0.07
    emez
    0.07
    marsh
    0.07
    ãĤĩ
    0.07
    ibo
    0.06
    ãģĵãĤĵãģ«
    0.06
    olean
    0.06
    resco
    0.06
    _via
    0.06
    fila
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.