© 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. 55255
    Prev
    Next
    INDEX
    Explanations

    references to fantasy genres and their associated themes

    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
    dum
    -0.22
     Dip
    -0.21
     dipping
    -0.20
    dio
    -0.19
     Dome
    -0.18
    dish
    -0.17
     deduct
    -0.17
    dere
    -0.16
    Dummy
    -0.16
     Dias
    -0.16
    POSITIVE LOGITS
     drag
    0.84
     Drag
    0.80
    drag
    0.78
    Drag
    0.77
     dragon
    0.72
     DR
    0.71
    .drag
    0.70
     Dragon
    0.69
     dr
    0.68
     dragons
    0.66
    Activations Density 0.006%

    No Known Activations