© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 43258
    Prev
    Next
    INDEX
    Explanations

    references to symbols, specifically those related to religion or iconic imagery

    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
    GIN
    -0.14
    rollo
    -0.14
    owitz
    -0.14
    ิà¹Ĥ
    -0.13
    aki
    -0.13
    ãĥ¼ãĥľ
    -0.13
    ابع
    -0.13
    alse
    -0.13
    cak
    -0.13
    .AutoComplete
    -0.13
    POSITIVE LOGITS
     cross
    0.32
     crossed
    0.30
     Cross
    0.28
    -cross
    0.28
     crosses
    0.28
    cross
    0.26
    Cross
    0.25
     CROSS
    0.24
     symbol
    0.24
     styl
    0.22
    Activations Density 0.059%

    No Known Activations