© 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. 55088
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and their associated values

    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
     Stevenson
    -0.16
     Sark
    -0.15
     Sanders
    -0.15
    stalk
    -0.14
     Spi
    -0.14
     Slug
    -0.14
     Sync
    -0.14
     Sharma
    -0.14
     Spicer
    -0.14
     defaultCenter
    -0.14
    POSITIVE LOGITS
     square
    0.58
     Squ
    0.57
     squ
    0.56
     Square
    0.54
     sq
    0.50
    -square
    0.47
     SQ
    0.46
     Sq
    0.46
    Square
    0.45
    square
    0.44
    Activations Density 0.020%

    No Known Activations