© 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. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 26196
    Prev
    Next
    INDEX
    Explanations

    words related to regulations, policies, and requirements concerning personal appearance and grooming standards

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     inval
    -0.19
    nul
    -0.17
    stro
    -0.13
     erotik
    -0.13
    unma
    -0.13
     ZákladnÃŃ
    -0.13
    uld
    -0.13
    pas
    -0.13
     dÃŃv
    -0.12
    rou
    -0.12
    POSITIVE LOGITS
     reasonably
    0.22
     reasonable
    0.22
    reasonable
    0.20
    reason
    0.18
     written
    0.17
     Reason
    0.16
     accompany
    0.16
     reasons
    0.15
    written
    0.15
     accompanies
    0.15
    Activations Density 0.170%

    No Known Activations