© 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. 15491
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to animals and their aspects

    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
     çī
    -0.17
     Cort
    -0.17
     Opcode
    -0.16
     Coral
    -0.15
    contri
    -0.15
    elves
    -0.14
    finity
    -0.14
     pitches
    -0.14
     monkeys
    -0.14
    tainment
    -0.14
    POSITIVE LOGITS
     duck
    0.52
     ducks
    0.50
     Duck
    0.50
    duck
    0.47
     Ducks
    0.46
     goose
    0.40
     Goose
    0.36
     mall
    0.31
    DU
    0.31
     ge
    0.29
    Activations Density 0.011%

    No Known Activations