© 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. 30470
    Prev
    Next
    INDEX
    Explanations

    words or suffixes related to cautionary or advisory themes

    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
    st
    -0.33
    sto
    -0.23
    ly
    -0.23
    ened
    -0.22
    sti
    -0.21
    ively
    -0.20
    ned
    -0.20
    sta
    -0.20
    sty
    -0.20
    ally
    -0.20
    POSITIVE LOGITS
    yyyy
    0.32
    yyy
    0.32
    lation
    0.28
    ship
    0.24
    yy
    0.22
    tics
    0.22
    outube
    0.21
    town
    0.21
    esterday
    0.21
    thon
    0.21
    Activations Density 0.060%

    No Known Activations