© 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. 14612
    Prev
    Next
    INDEX
    Explanations

    references to the word "high," particularly in educational or competitive contexts

    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
    ieren
    -0.17
    ÑĢиÑĤи
    -0.14
     odak
    -0.14
     Sovere
    -0.14
    ade
    -0.14
     Tyson
    -0.14
    ies
    -0.14
    ments
    -0.13
    M
    -0.13
     Neo
    -0.13
    POSITIVE LOGITS
     school
    0.53
    school
    0.47
     School
    0.41
    -school
    0.40
     SCHOOL
    0.39
     schools
    0.39
    _school
    0.37
    School
    0.35
    .school
    0.34
    chool
    0.33
    Activations Density 0.022%

    No Known Activations