© 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 EvalsExportsinterp-engineNEWAPI 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. 123644
    Prev
    Next
    INDEX
    Explanations

    patterns in programming structures, specifically related to function definitions and return values

    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
    hoff
    -0.07
     latter
    -0.06
    ohan
    -0.06
    ayacak
    -0.06
    ohn
    -0.06
    upe
    -0.06
    wire
    -0.06
    allo
    -0.06
    wald
    -0.06
    reff
    -0.06
    POSITIVE LOGITS
    enia
    0.07
     returnValue
    0.06
    agher
    0.06
    elez
    0.06
     kå
    0.06
    ynet
    0.06
    Ñģлов
    0.06
    imiter
    0.06
     pretext
    0.06
     okol
    0.06
    Activations Density 0.009%

    No Known Activations