© 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. 14916
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical notation or programming-related terms

    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
     Pang
    -0.16
    ahu
    -0.15
    èįIJ
    -0.14
     exhaust
    -0.14
    ãĥ³ãĥIJ
    -0.14
    ãģ»ãģĨ
    -0.14
    refix
    -0.13
    æģĴ
    -0.13
    /ws
    -0.13
    ursor
    -0.12
    POSITIVE LOGITS
    ry
    0.36
    ey
    0.33
    ary
    0.33
    ery
    0.32
    ory
    0.31
    ay
    0.31
    ty
    0.30
    py
    0.29
    ony
    0.28
    RY
    0.28
    Activations Density 0.020%

    No Known Activations