© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 28449
    Prev
    Next
    INDEX
    Explanations

    references to various types of computers and their condition

    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
     computers
    -0.41
     Computers
    -0.41
     computer
    -0.33
     Computer
    -0.32
     COMPUTER
    -0.30
    computer
    -0.29
    Computer
    -0.28
     computed
    -0.26
    Comput
    -0.26
     Computing
    -0.25
    POSITIVE LOGITS
     peripheral
    0.23
     peripherals
    0.20
     mobile
    0.20
    phony
    0.18
     Peripheral
    0.18
     Mac
    0.17
    .habbo
    0.17
     MAC
    0.17
     Mobile
    0.16
    aign
    0.16
    Activations Density 0.009%

    No Known Activations