© 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. 24373
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and identity in a wartime context

    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
    reed
    -0.16
     Åŀu
    -0.14
     Kültür
    -0.14
    urger
    -0.14
    ermal
    -0.14
    /******/
    -0.14
    ushima
    -0.14
    etro
    -0.14
    Merit
    -0.14
    InstantiationException
    -0.14
    POSITIVE LOGITS
    192
    0.17
     Violet
    0.15
     wireless
    0.15
     aged
    0.15
     Jack
    0.15
    åŃĹ
    0.15
     JACK
    0.15
     Alf
    0.15
     pip
    0.15
    vr
    0.15
    Activations Density 0.027%

    No Known Activations