© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 81006
    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
     coloring
    -0.06
    ç¢
    -0.06
    swick
    -0.06
     Danh
    -0.06
    oya
    -0.06
    :request
    -0.06
     favored
    -0.06
     fus
    -0.05
     jspb
    -0.05
     AUX
    -0.05
    POSITIVE LOGITS
    combe
    0.07
    dent
    0.07
    inz
    0.06
    dana
    0.06
    insula
    0.06
    iyim
    0.06
     McMaster
    0.06
    .openapi
    0.06
     -*-č↵
    0.06
    ’ta
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.