© 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. 21230
    Prev
    Next
    INDEX
    Explanations

    phrases indicating current status or developments

    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
    izu
    -0.17
    AREST
    -0.15
    947
    -0.15
    ITED
    -0.15
    åĬ¨çĶŁæĪIJ
    -0.15
    ERGE
    -0.14
    jvu
    -0.14
    ÙĪØ«
    -0.14
    ë¡ľëĵľ
    -0.14
     IReadOnly
    -0.14
    POSITIVE LOGITS
     entering
    0.56
     enter
    0.47
     enters
    0.47
    enter
    0.46
    Entering
    0.45
     Enter
    0.42
     entered
    0.39
    -enter
    0.39
    Enter
    0.38
    .enter
    0.37
    Activations Density 0.016%

    No Known Activations