© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 15243
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and judicial decisions

    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
    INDER
    -0.19
    @nate
    -0.17
    inder
    -0.16
    ulton
    -0.15
    zel
    -0.15
     Votes
    -0.15
    íĨłíĨł
    -0.14
    ullet
    -0.14
    UDO
    -0.14
     ADVISED
    -0.14
    POSITIVE LOGITS
     High
    0.28
     HC
    0.26
     Sessions
    0.25
     court
    0.23
    HC
    0.23
    High
    0.23
     high
    0.22
     bench
    0.22
     sessions
    0.21
     lower
    0.21
    Activations Density 0.018%

    No Known Activations