© 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 EvalsExportsinterp-engineNEWAPI 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. 21904
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate representation or significant changes

    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
    onn
    -0.15
    readcr
    -0.15
    ibs
    -0.15
    ya
    -0.14
    spar
    -0.14
    URA
    -0.14
    zn
    -0.13
    ìĸ´ìĦľ
    -0.13
    _PATCH
    -0.13
    osto
    -0.13
    POSITIVE LOGITS
     Ñģобой
    0.41
     ÑģобоÑİ
    0.30
    ize
    0.17
    ational
    0.17
    ä¸įäºĨ
    0.17
     part
    0.17
    izes
    0.16
    atively
    0.16
    ively
    0.16
    lage
    0.16
    Activations Density 0.101%

    No Known Activations