© 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. 14986
    Prev
    Next
    INDEX
    Explanations

    names of athletes and references to sports contracts

    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
    assen
    -0.17
    èĿ
    -0.15
    stm
    -0.15
     Hugo
    -0.14
    ãĥ´ãĤ¡
    -0.13
    elop
    -0.13
    .lp
    -0.13
    LTR
    -0.13
    ibar
    -0.12
    immers
    -0.12
    POSITIVE LOGITS
    ichick
    0.18
     Bias
    0.17
     Emb
    0.16
    onio
    0.15
    anton
    0.15
    antan
    0.15
    toolbox
    0.15
    adian
    0.15
    -signed
    0.14
    orny
    0.14
    Activations Density 0.049%

    No Known Activations