© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 38291
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax and data structures

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ç´ł
    -0.06
     UIResponder
    -0.06
    utex
    -0.06
    éģĵ
    -0.06
    elmet
    -0.06
    олиÑĤ
    -0.06
    antically
    -0.06
    DIV
    -0.06
    é¾Ħ
    -0.06
    built
    -0.06
    POSITIVE LOGITS
    ίγ
    0.07
    alg
    0.07
    é®
    0.07
     Stocks
    0.06
    tainment
    0.06
    enville
    0.06
    оÑĢож
    0.06
    esel
    0.06
    ÙĨدگÛĮ
    0.06
    nore
    0.06
    Activations Density 0.070%

    No Known Activations