© 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. 23905
    Prev
    Next
    INDEX
    Explanations

    words associated with conflict and physical altercations

    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
    eries
    -0.15
    otine
    -0.15
    ileo
    -0.14
     Prep
    -0.14
    icone
    -0.14
    ặt
    -0.14
    idge
    -0.14
     addCriterion
    -0.14
    ingles
    -0.14
    upal
    -0.13
    POSITIVE LOGITS
     ended
    0.27
     turned
    0.27
     gone
    0.27
     ends
    0.26
     ending
    0.26
     turns
    0.26
     Ending
    0.25
     turning
    0.24
     Turn
    0.23
    Ending
    0.23
    Activations Density 0.017%

    No Known Activations