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

    Neuronpedia

    APICircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5688
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure indicative of coding practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    etta
    -0.08
    .UTC
    -0.07
    irteen
    -0.07
    ChangedEventArgs
    -0.07
    etro
    -0.07
    wap
    -0.07
     )↵↵↵↵↵↵↵↵
    -0.07
    ews
    -0.07
    _helpers
    -0.06
    EMON
    -0.06
    POSITIVE LOGITS
     private
    0.08
     public
    0.08
     final
    0.07
    final
    0.06
     int
    0.06
    private
    0.06
    954
    0.06
    jee
    0.06
    int
    0.06
     Ba
    0.06
    Activations Density 0.003%

    No Known Activations