© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41187
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms related to complex calculations

    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
    zier
    -0.15
     (~(
    -0.15
    VML
    -0.15
    ẩu
    -0.15
    .setPosition
    -0.14
    maal
    -0.14
    acon
    -0.14
    ī´
    -0.14
     Bent
    -0.14
    /umd
    -0.13
    POSITIVE LOGITS
     x
    0.42
     X
    0.34
     horizontal
    0.33
    x
    0.33
    .x
    0.30
    _x
    0.30
     y
    0.29
    X
    0.28
     vertical
    0.28
     Horizontal
    0.28
    Activations Density 0.020%

    No Known Activations