© 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. 126947
    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
    idor
    -0.07
    à¥Ĥà¤ģ
    -0.06
    èĥ½å¤Ł
    -0.06
    icari
    -0.06
    ::-
    -0.06
    ç´
    -0.06
    ÏĨα
    -0.06
    532
    -0.06
    åIJĪ
    -0.06
     *\
    -0.06
    POSITIVE LOGITS
    plx
    0.07
     hero
    0.07
    ixer
    0.06
    :frame
    0.06
     peak
    0.06
    uy
    0.06
    okit
    0.06
    zens
    0.06
    unan
    0.06
    itchens
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.