© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78829
    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
    _secs
    -0.07
     Stuff
    -0.06
    alth
    -0.06
     congen
    -0.06
    duit
    -0.06
    aidu
    -0.06
    imbus
    -0.06
     íķĦìļĶíķľ
    -0.06
    kus
    -0.06
    ["$
    -0.06
    POSITIVE LOGITS
    beros
    0.07
     Animalia
    0.07
    jal
    0.07
    ãĤ·ãĤ¢
    0.07
    ãĥ¼ãĤ¯
    0.06
    é³
    0.06
     alike
    0.06
    itone
    0.06
    âĻ¡
    0.06
    .sax
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.