© 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 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. 43067
    Prev
    Next
    INDEX
    Explanations

    mentions of the abbreviation "UT" or variations thereof

    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
    oon
    -0.18
     Folk
    -0.16
    oons
    -0.16
    .acquire
    -0.16
    meli
    -0.15
    ool
    -0.15
     Atlas
    -0.15
    aska
    -0.15
    oq
    -0.15
    vip
    -0.14
    POSITIVE LOGITS
    IBE
    0.17
    leans
    0.15
    .tex
    0.15
    thon
    0.15
    AH
    0.15
    ahas
    0.15
    arak
    0.14
     Austin
    0.14
    ah
    0.14
     TestUtils
    0.14
    Activations Density 0.004%

    No Known Activations