© 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. 21690
    Prev
    Next
    INDEX
    Explanations

    references to international relations and agreements between countries

    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
    auen
    -0.15
    òi
    -0.14
     пÑĢава
    -0.14
    borg
    -0.14
    oje
    -0.14
    &action
    -0.14
    à¸į
    -0.14
     curly
    -0.13
    権
    -0.13
    usercontent
    -0.13
    POSITIVE LOGITS
     bilateral
    0.37
     bil
    0.34
     Bil
    0.33
     mutual
    0.31
    bil
    0.29
     mutually
    0.28
     exchanged
    0.25
     Mutual
    0.24
     exchange
    0.23
     exchanges
    0.23
    Activations Density 0.083%

    No Known Activations