© 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. 21030
    Prev
    Next
    INDEX
    Explanations

    statements related to professional qualifications and experience

    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
    ething
    -0.15
    她们
    -0.14
    arser
    -0.13
    \Context
    -0.13
    angu
    -0.13
    .Companion
    -0.13
    úb
    -0.12
    agos
    -0.12
    avigator
    -0.12
    angelo
    -0.12
    POSITIVE LOGITS
     his
    0.35
    his
    0.27
     His
    0.26
    His
    0.26
     besides
    0.25
    ä»ĸçļĦ
    0.25
     he
    0.25
     prior
    0.23
     aside
    0.22
    ä»ĸ
    0.22
    Activations Density 0.311%

    No Known Activations