© 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. 42112
    Prev
    Next
    INDEX
    Explanations

    the word "but" and its variations, indicating contrasts or exceptions in context

    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
     alike
    -0.16
    olly
    -0.16
    ziel
    -0.15
    strcasecmp
    -0.15
    oley
    -0.15
     Tang
    -0.15
     susp
    -0.15
    ops
    -0.14
    duct
    -0.14
    бо
    -0.14
    POSITIVE LOGITS
    term
    0.27
    lers
    0.25
    ters
    0.25
    ler
    0.24
    ressed
    0.24
    ressing
    0.23
    chers
    0.22
    ts
    0.22
    cher
    0.21
    tpl
    0.21
    Activations Density 0.018%

    No Known Activations