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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21747
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to significance or interpretation

    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
    ipa
    -0.16
    ãĥ«ãĥī
    -0.16
    urch
    -0.15
    uggy
    -0.15
    imits
    -0.15
    bury
    -0.14
    /remove
    -0.14
    -mounted
    -0.14
    elog
    -0.14
    ypi
    -0.14
    POSITIVE LOGITS
    fully
    0.38
    lessness
    0.33
    fulness
    0.29
    ful
    0.28
    full
    0.27
    FUL
    0.26
    FULL
    0.23
    lessly
    0.22
     behind
    0.22
    less
    0.22
    Activations Density 0.013%

    No Known Activations