© 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. 108738
    Prev
    Next
    INDEX
    Explanations

    code or syntax elements related to programming and parsing functions

    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
     paramMap
    -0.07
    oningen
    -0.06
    ús
    -0.06
    bruary
    -0.06
    cri
    -0.06
    ibern
    -0.06
    phia
    -0.06
    ampp
    -0.06
    enario
    -0.06
    çļĦä¸Ģ个
    -0.06
    POSITIVE LOGITS
    ĨĴ
    0.07
     echo
    0.07
     PropertyValue
    0.07
    echo
    0.06
     touch
    0.06
    ega
    0.06
     tee
    0.06
    setAttribute
    0.06
     volta
    0.06
     Burst
    0.06
    Activations Density 0.004%

    No Known Activations