© 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. 29499
    Prev
    Next
    INDEX
    Explanations

    terms related to executions and the death penalty

    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
     subpoena
    -0.14
    amage
    -0.14
    erson
    -0.14
    oras
    -0.14
    ierce
    -0.14
    wil
    -0.14
    .desktop
    -0.13
    ileges
    -0.13
     harassing
    -0.13
    ãĥ¡ãĥ©
    -0.13
    POSITIVE LOGITS
     death
    0.41
     executions
    0.40
     execution
    0.39
     Death
    0.39
     Execution
    0.35
    death
    0.35
    Death
    0.34
    execution
    0.32
    -death
    0.31
    Execution
    0.30
    Activations Density 0.019%

    No Known Activations