© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93626
    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
    baum
    -0.07
    ovit
    -0.06
    //*[@
    -0.06
    //*[
    -0.06
     Judiciary
    -0.06
    antd
    -0.06
    atum
    -0.06
    گاÙĨÛĮ
    -0.06
    جÙħ
    -0.05
     Pawn
    -0.05
    POSITIVE LOGITS
    www
    0.12
    s
    0.09
     www
    0.08
    localhost
    0.08
    127
    0.07
    elp
    0.07
    ERVED
    0.07
    .docs
    0.07
    roker
    0.07
    arie
    0.07
    Activations Density 0.024%

    No Known Activations