© 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. 60926
    Prev
    Next
    INDEX
    Explanations

    occurrences of code-related expressions or functions

    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
    anken
    -0.07
    et
    -0.07
    cdc
    -0.07
    .IsNull
    -0.06
     tay
    -0.06
    achs
    -0.06
     strategy
    -0.06
    Å¡k
    -0.06
    ffff
    -0.06
    Ñīей
    -0.06
    POSITIVE LOGITS
    233
    0.07
    -notification
    0.07
    elerik
    0.06
    /gtest
    0.06
     stringWith
    0.06
    imits
    0.06
    fos
    0.06
    Ù¢
    0.06
     AppleWebKit
    0.06
    ieval
    0.05
    Activations Density 0.006%

    No Known Activations