© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3792
    Prev
    Next
    INDEX
    Explanations

    instances of function definitions 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
    $MESS
    -0.07
    unca
    -0.07
    rschein
    -0.07
    erman
    -0.06
    ury
    -0.06
    uria
    -0.06
    ernote
    -0.06
    ermen
    -0.06
    ourage
    -0.06
    Â
    -0.06
    POSITIVE LOGITS
     const
    0.06
    annels
    0.06
    онов
    0.06
    erva
    0.06
     Punch
    0.06
     Rogers
    0.06
     alc
    0.06
    Ī
    0.05
    allon
    0.05
    otros
    0.05
    Activations Density 0.001%

    No Known Activations