© 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. 24395
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and phrases indicating web browsing activity

    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
    uco
    -0.15
    ports
    -0.15
    iest
    -0.15
    dorf
    -0.15
    =./
    -0.15
    ushman
    -0.15
    ijk
    -0.14
    oningen
    -0.14
    ware
    -0.14
    yleft
    -0.14
    POSITIVE LOGITS
     internet
    0.52
     Internet
    0.50
    Internet
    0.45
    internet
    0.42
     INTERN
    0.37
    äºĴèģĶç½ij
    0.30
     web
    0.28
     Web
    0.26
    ternet
    0.25
     net
    0.24
    Activations Density 0.069%

    No Known Activations