© 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. 14956
    Prev
    Next
    INDEX
    Explanations

    instances of data structure declarations 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
    tg
    -0.07
    .Logf
    -0.07
    ersh
    -0.06
    rosse
    -0.06
    utable
    -0.06
     Vác
    -0.06
    petition
    -0.06
    renom
    -0.06
    erno
    -0.06
    anner
    -0.06
    POSITIVE LOGITS
    StackSize
    0.07
    conv
    0.07
     Keller
    0.06
     Webb
    0.06
    imbus
    0.06
     Salt
    0.06
     Holl
    0.06
     trao
    0.06
    STA
    0.06
     Christian
    0.06
    Activations Density 0.000%

    No Known Activations