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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 96028
    Prev
    Next
    INDEX
    Explanations

    references to data types in programming contexts

    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
    iform
    -0.07
    ary
    -0.06
    unte
    -0.06
     quadr
    -0.06
    ,
    -0.06
    ardy
    -0.06
    Ìģ
    -0.06
     movies
    -0.05
     bureau
    -0.05
     victorious
    -0.05
    POSITIVE LOGITS
    -License
    0.08
    ------↵↵
    0.08
    дам
    0.07
    VRT
    0.07
    $LANG
    0.07
    rupa
    0.07
    ãİ
    0.07
    /Sub
    0.07
    ,},↵
    0.07
    >>>(
    0.07
    Activations Density 0.011%

    No Known Activations