© 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. 44192
    Prev
    Next
    INDEX
    Explanations

    instances of the word "look" or its derivatives, indicating searches or observations

    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
    search
    -0.18
    .generated
    -0.16
     Search
    -0.16
    Search
    -0.16
     lookup
    -0.16
    _search
    -0.15
    _Search
    -0.15
    chk
    -0.15
    ega
    -0.15
     search
    -0.15
    POSITIVE LOGITS
     for
    0.46
    	for
    0.31
    for
    0.29
    _for
    0.24
     untuk
    0.23
    ForKey
    0.23
    สำหร
    0.23
     για
    0.22
     voor
    0.22
     ÙĦÙĦØŃ
    0.22
    Activations Density 0.033%

    No Known Activations