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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 107070
    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
     célib
    -0.07
     Stout
    -0.07
     maduras
    -0.07
    ëĿ½
    -0.07
    stuff
    -0.07
    ãĥ»ãĥ»ãĥ»↵↵
    -0.07
    YNAM
    -0.07
    Enumerator
    -0.07
    ¦æĥħ
    -0.07
    ัà¸ĩà¸ģ
    -0.07
    POSITIVE LOGITS
     international
    0.08
     global
    0.08
    global
    0.07
    rs
    0.06
     междÑĥнаÑĢод
    0.06
     Global
    0.06
    international
    0.06
     Paren
    0.06
    icularly
    0.06
    ’
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.