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. 43983
    Prev
    Next
    INDEX
    Explanations

    function prototypes and parameter annotations in code snippets

    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
    ónico
    -0.06
    gis
    -0.06
     Merchant
    -0.06
    ContentSize
    -0.05
    orado
    -0.05
    kir
    -0.05
     pione
    -0.05
     articles
    -0.05
    APE
    -0.05
    ches
    -0.05
    POSITIVE LOGITS
    note
    0.13
    remark
    0.12
     note
    0.12
    warning
    0.12
    retval
    0.12
    remarks
    0.11
    sa
    0.11
     warning
    0.10
    param
    0.10
    Note
    0.10
    Activations Density 0.010%

    No Known Activations