© 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. 23794
    Prev
    Next
    INDEX
    Explanations

    references to researchers or authors, particularly their last names

    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
    aise
    -0.22
    ound
    -0.20
    ates
    -0.19
    ange
    -0.19
    ain
    -0.18
    andom
    -0.18
    ади
    -0.17
    oller
    -0.17
    ate
    -0.16
    anch
    -0.16
    POSITIVE LOGITS
    ios
    0.20
    nj
    0.18
    icket
    0.17
    ynes
    0.16
    asan
    0.16
    ar
    0.15
    imens
    0.15
    alley
    0.14
    ζα
    0.14
    il
    0.14
    Activations Density 0.020%

    No Known Activations