© 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. 55156
    Prev
    Next
    INDEX
    Explanations

    words related to military or militant groups

    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
    atik
    -0.15
    hid
    -0.15
    omain
    -0.15
    rové
    -0.15
    .cls
    -0.15
    plusplus
    -0.14
     Ala
    -0.14
     Dak
    -0.14
    ERG
    -0.14
    yalty
    -0.14
    POSITIVE LOGITS
    ancy
    0.29
    arily
    0.28
     ary
    0.23
    aries
    0.23
    ARY
    0.22
    airy
    0.22
    antly
    0.22
    ary
    0.19
    arry
    0.18
    arty
    0.18
    Activations Density 0.003%

    No Known Activations