© 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. 41966
    Prev
    Next
    INDEX
    Explanations

    terms related to jihadism and conflicts involving jihadist 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
    _json
    -0.20
    joint
    -0.20
    json
    -0.19
    Json
    -0.19
     Jewish
    -0.19
    /job
    -0.18
    _joint
    -0.17
     judgment
    -0.17
    judge
    -0.17
     judicial
    -0.17
    POSITIVE LOGITS
     Bản
    0.23
    venile
    0.23
    ifiable
    0.20
    uxtap
    0.20
    ÅĽli
    0.19
    stice
    0.19
    ventus
    0.18
    ery
    0.17
    ecs
    0.17
    uggling
    0.17
    Activations Density 0.194%

    No Known Activations