Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96077
    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
    alta
    -0.07
     gord
    -0.06
    ereotype
    -0.06
    èĻİ
    -0.06
    adj
    -0.06
    âĢĥ
    -0.06
    æ¨
    -0.06
    asure
    -0.06
    erie
    -0.06
    erus
    -0.06
    POSITIVE LOGITS
    ureka
    0.07
    acman
    0.07
    gua
    0.07
    uesta
    0.06
    ÏĦον
    0.06
    usat
    0.06
    alfa
    0.06
    bedo
    0.06
    ÙĬÙĤ
    0.06
    SPATH
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.