© 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. 53951
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs and actions related to attempts or efforts

    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
    enza
    -0.14
    è¦
    -0.14
     offering
    -0.14
    quin
    -0.13
     Charter
    -0.13
    wig
    -0.13
     Gill
    -0.13
    adoras
    -0.13
    ayout
    -0.13
    byn
    -0.12
    POSITIVE LOGITS
     draw
    0.65
     draws
    0.60
     drawing
    0.60
     Draw
    0.58
    Draw
    0.56
     drew
    0.55
     Draws
    0.54
     drawn
    0.54
    draw
    0.53
     Drawing
    0.52
    Activations Density 0.028%

    No Known Activations