© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 63601
    Prev
    Next
    INDEX
    Explanations

    instances of injury or harm in a narrative

    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
    »¿
    -0.15
     Destructor
    -0.15
     destructive
    -0.15
    imid
    -0.14
    ilos
    -0.14
    ovol
    -0.14
    isin
    -0.13
    Susp
    -0.13
    .isFile
    -0.13
    ngth
    -0.13
    POSITIVE LOGITS
     shot
    0.36
     wounded
    0.30
     wounds
    0.29
    -shot
    0.29
     dying
    0.29
    shot
    0.28
     bullet
    0.28
     fatally
    0.28
     shots
    0.28
     wound
    0.27
    Activations Density 0.057%

    No Known Activations