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. 31-LLAMASCOPE-RES-131K
    6. 44341
    Prev
    Next
    INDEX
    Explanations

    statements related to imports and package declarations in programming code

    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
    upert
    -0.07
    ymoon
    -0.07
    etat
    -0.07
     Inner
    -0.07
    clearfix
    -0.07
    nder
    -0.07
     ifdef
    -0.07
    ãĥ¼ãĥģ
    -0.07
    peq
    -0.07
    á»ijc
    -0.06
    POSITIVE LOGITS
    import
    0.10
     import
    0.06
     worth
    0.06
    uzzer
    0.06
    ......
    0.06
    /*------------------------------------------------
    0.05
    /*****************************************************************************↵
    0.05
    LF
    0.05
    umor
    0.05
     Sessions
    0.05
    Activations Density 0.010%

    No Known Activations