© 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. 28856
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or contrast

    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
     myself
    -0.69
     my
    -0.68
     saya
    -0.58
    æĪij
    -0.58
     tôi
    -0.58
     I
    -0.54
    æĪijçļĦ
    -0.54
    让æĪij
    -0.50
     minha
    -0.48
     Tôi
    -0.48
    POSITIVE LOGITS
     ourselves
    0.46
     ours
    0.38
     we
    0.34
    ours
    0.32
    æĪijåĢij
    0.31
     our
    0.30
    æĪij们
    0.29
    —we
    0.29
    .Our
    0.28
     noi
    0.28
    Activations Density 0.006%

    No Known Activations