© 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. 124580
    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
    277
    -0.06
    ó
    -0.06
    .ErrorMessage
    -0.06
    yat
    -0.06
     architekt
    -0.06
    centroid
    -0.06
    wang
    -0.06
    @nate
    -0.06
    loat
    -0.06
     Kil
    -0.06
    POSITIVE LOGITS
    efa
    0.07
    unci
    0.07
    еÑģÑĮ
    0.07
    ĥģ
    0.06
    ihan
    0.06
    rav
    0.06
    nave
    0.06
    andr
    0.06
    ields
    0.06
    ivate
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.