© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 63491
    Prev
    Next
    INDEX
    Explanations

    mentions of trial-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    eland
    -0.23
    вен
    -0.16
    venir
    -0.15
    ãĤ«ãĥ«
    -0.14
    croft
    -0.14
    gem
    -0.14
    aad
    -0.14
    seller
    -0.14
    aos
    -0.13
    ;element
    -0.13
    POSITIVE LOGITS
    ogue
    0.28
     balloon
    0.22
     nghiá»ĩm
    0.21
     balance
    0.20
     run
    0.19
    ufe
    0.18
     balloons
    0.18
    -by
    0.18
     Balance
    0.17
    _RUN
    0.17
    Activations Density 0.007%

    No Known Activations