© 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. 77340
    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
    ↵↵
    -0.06
    abit
    -0.06
     previously
    -0.06
     Attempt
    -0.06
    _macros
    -0.06
     moż
    -0.05
    å¹³æĪIJ
    -0.05
    acre
    -0.05
    ìŀ¡
    -0.05
     badass
    -0.05
    POSITIVE LOGITS
    uft
    0.08
    /WebAPI
    0.07
    даÑı
    0.07
    elage
    0.07
    หว
    0.07
    rve
    0.07
    对æĸ¹
    0.07
     ÄĮer
    0.07
    WND
    0.07
    tel
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.