© 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. 15-LLAMASCOPE-RES-131K
    11. 86707
    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
    275
    -0.07
    sten
    -0.06
    co
    -0.06
    app
    -0.06
    sets
    -0.06
    me
    -0.06
    our
    -0.06
    ny
    -0.06
     INTERN
    -0.06
    ner
    -0.06
    POSITIVE LOGITS
    edException
    0.08
    oš
    0.08
    edList
    0.08
    veau
    0.07
    νÏī
    0.07
    stants
    0.07
    icros
    0.07
    otime
    0.07
    theid
    0.07
    алÑİ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.