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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 41320
    Prev
    Next
    INDEX
    Explanations

    references to quantities and measurements

    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
    uml
    -0.13
    ysl
    -0.13
    chwitz
    -0.13
    ëłĪìĬ¤
    -0.12
    ÅĻez
    -0.12
    кÑĥÑĤ
    -0.12
     coz
    -0.12
     th
    -0.12
    tÄĽÅ¾
    -0.12
     üzerinde
    -0.12
    POSITIVE LOGITS
     twice
    0.58
     Twice
    0.44
     half
    0.42
    half
    0.35
     Half
    0.32
     HALF
    0.32
    -half
    0.29
    åįĬ
    0.28
    Half
    0.28
     equal
    0.27
    Activations Density 0.156%

    No Known Activations