© 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 EvalsExportsinterp-engineNEWAPI 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. 24615
    Prev
    Next
    INDEX
    Explanations

    instances of conflict or confrontation in dialogues

    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
     his
    -0.37
    his
    -0.31
     he
    -0.29
    ä»ĸçļĦ
    -0.28
     him
    -0.27
     jeho
    -0.25
     его
    -0.25
    ä»ĸ
    -0.24
     jego
    -0.24
     zijn
    -0.24
    POSITIVE LOGITS
     things
    0.28
     eventually
    0.26
     someone
    0.24
     temp
    0.23
    Eventually
    0.23
    someone
    0.23
     Eventually
    0.22
    things
    0.22
    Things
    0.21
     tension
    0.21
    Activations Density 0.036%

    No Known Activations