© 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. 21084
    Prev
    Next
    INDEX
    Explanations

    terms related to wavelet technology and its applications in image and facial recognition

    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
    rev
    -0.18
    .UnitTesting
    -0.17
    wahl
    -0.17
    ÑĥÑĢн
    -0.16
    ./(
    -0.16
    thon
    -0.16
    reads
    -0.15
    èīĩ
    -0.15
    à¹Ĥà¸Ļ
    -0.15
    ##_
    -0.15
    POSITIVE LOGITS
    guide
    0.31
    forms
    0.29
    front
    0.28
     goodbye
    0.26
    let
    0.24
    guid
    0.23
    function
    0.22
    crest
    0.20
    LENGTH
    0.19
    formData
    0.18
    Activations Density 0.011%

    No Known Activations