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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 119216
    Prev
    Next
    INDEX
    Explanations

    C++ standard library components and operators related to stream output and error handling

    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
    656
    -0.06
    fee
    -0.06
    itler
    -0.06
     walk
    -0.06
    ual
    -0.06
    thood
    -0.06
     fee
    -0.06
    ollections
    -0.06
    awai
    -0.06
    avo
    -0.06
    POSITIVE LOGITS
    (æ°´
    0.06
    iskey
    0.06
    vars
    0.06
    icks
    0.06
    /ajax
    0.06
     جاÙħع
    0.06
     Shields
    0.06
    asin
    0.06
    UPI
    0.06
     vars
    0.06
    Activations Density 0.006%

    No Known Activations