© 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. 117573
    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
    rrha
    -0.07
    uilder
    -0.06
    utely
    -0.06
    lops
    -0.06
    HING
    -0.06
    iene
    -0.06
    edImage
    -0.06
    ueba
    -0.06
    ueur
    -0.06
    ilia
    -0.06
    POSITIVE LOGITS
    setter
    0.07
     èĭ
    0.06
    apple
    0.06
     Johnston
    0.06
     size
    0.06
    ãĤ¤ãĤ¯
    0.06
    ssize
    0.06
     sized
    0.06
     Levy
    0.06
    ترÙĥ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.