© 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. 58259
    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
    haar
    -0.08
    792
    -0.07
    ifu
    -0.07
    976
    -0.07
    MBProgressHUD
    -0.06
    648
    -0.06
    æk
    -0.06
    643
    -0.06
    375
    -0.06
     noqa
    -0.06
    POSITIVE LOGITS
    ìĭ¬
    0.07
    ãĥ¼ãĥĨ
    0.06
    ;s
    0.06
    acades
    0.06
    aci
    0.06
    ocz
    0.06
     пода
    0.06
    _Node
    0.06
    มห
    0.06
    ãĤ¯ãĥĪ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.