© 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. 15161
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or opinions

    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
    iggins
    -0.16
    ogle
    -0.16
    илÑı
    -0.15
    iske
    -0.15
    rossover
    -0.14
    ukan
    -0.14
    inkel
    -0.14
    uv
    -0.13
    à¹ģà¸Ļ
    -0.13
    ewise
    -0.13
    POSITIVE LOGITS
     effectively
    1.01
     essentially
    0.79
    effect
    0.68
     basically
    0.66
     effective
    0.64
     Effect
    0.61
     Essentially
    0.57
    Effect
    0.56
    ess
    0.56
     Effective
    0.54
    Activations Density 0.038%

    No Known Activations