© 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. 108927
    Prev
    Next
    INDEX
    Explanations

    coding-related constructs and functions involving matches and exceptions

    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
    _:*
    -0.08
    ema
    -0.07
    (æĹ¥
    -0.07
    /../
    -0.07
    /gtest
    -0.07
     Evet
    -0.07
    zenÃŃ
    -0.07
    _stdio
    -0.07
    až
    -0.07
    reur
    -0.07
    POSITIVE LOGITS
    akis
    0.06
    gree
    0.06
    éf
    0.05
    ##_
    0.05
     Welcome
    0.05
    oris
    0.05
     either
    0.05
    ahoma
    0.05
    ëĵ¤
    0.05
     ta
    0.05
    Activations Density 0.043%

    No Known Activations