© 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. 9-LLAMASCOPE-RES-131K
    11. 98751
    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
    aster
    -0.07
     reason
    -0.06
    [
    -0.06
    *
    -0.06
    .
    -0.06
     --
    -0.06
    -
    -0.06
    oa
    -0.06
    ,
    -0.06
     chast
    -0.05
    POSITIVE LOGITS
    groundColor
    0.08
    ITCH
    0.08
    ActionCode
    0.07
    /rss
    0.07
    ogl
    0.07
    dre
    0.07
    oolStrip
    0.07
    .MenuStrip
    0.07
    riteln
    0.07
    _KEYWORD
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.