© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 22967
    Prev
    Next
    INDEX
    Explanations

    terms related to the evolving roles and specializations in design disciplines

    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
    ulin
    -0.16
    usercontent
    -0.16
    าศ
    -0.14
    олÑĮно
    -0.14
    cura
    -0.14
    >{!!
    -0.14
    atz
    -0.13
    arken
    -0.13
    tero
    -0.13
    ÙĪÙĦÛĮ
    -0.13
    POSITIVE LOGITS
     special
    0.94
    special
    0.89
     Special
    0.83
    Special
    0.80
     SPECIAL
    0.77
    -special
    0.77
     spécial
    0.76
    pecial
    0.74
    _special
    0.73
     specialization
    0.73
    Activations Density 0.033%

    No Known Activations