© 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. 14107
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases associated with escalating emotions and actions during a conflict

    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
    istrovstvÃŃ
    -0.16
    amilia
    -0.16
    ALAR
    -0.15
    reopen
    -0.15
    ingleton
    -0.15
    jabi
    -0.15
     cyn
    -0.15
    #index
    -0.14
    олов
    -0.14
    fortunate
    -0.14
    POSITIVE LOGITS
     mean
    0.23
     comb
    0.23
     possess
    0.22
     hostile
    0.21
     abusive
    0.20
     violent
    0.20
     jealous
    0.20
     aggressive
    0.19
     trigger
    0.18
    comb
    0.18
    Activations Density 0.038%

    No Known Activations