© 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. 82021
    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
    racial
    -0.06
    ÛĮÙĩ
    -0.06
    ys
    -0.06
    cea
    -0.06
    esson
    -0.06
    ARY
    -0.06
    SENS
    -0.06
    Ether
    -0.06
    ̧
    -0.06
    zym
    -0.06
    POSITIVE LOGITS
    arine
    0.07
    etten
    0.06
    .joda
    0.06
    celik
    0.06
    iced
    0.06
    opus
    0.06
    inct
    0.06
    оÑĢож
    0.06
    uido
    0.06
    rvine
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.