© 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. 40963
    Prev
    Next
    INDEX
    Explanations

    programming variables and boolean flags in code

    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
    .updateDynamic
    -0.15
    оди
    -0.14
    (çģ«
    -0.13
    .scalablytyped
    -0.13
    uiten
    -0.13
     ëĦ¤ìĿ´íĬ¸
    -0.13
    пÑĢиклад
    -0.13
    ัศà¸Ļ
    -0.13
    .Reporting
    -0.13
    ëį°ìĿ´íĬ¸
    -0.13
    POSITIVE LOGITS
    eger
    0.13
     my
    0.12
     âĢ¦↵
    0.12
     main
    0.12
     Mane
    0.12
     target
    0.12
     `
    0.12
    aggable
    0.11
    âĢ²
    0.11
     s
    0.11
    Activations Density 0.152%

    No Known Activations