© 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. 8596
    Prev
    Next
    INDEX
    Explanations

    technical programming concepts and syntax

    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
    ẻ
    -0.17
     ëħĦëıĦë³Ħ
    -0.15
    æŀ¶
    -0.14
    [section
    -0.13
    IgnoreCase
    -0.13
     ÐļÑĢи
    -0.13
     gravity
    -0.13
    .downcase
    -0.13
    Idle
    -0.13
     ents
    -0.12
    POSITIVE LOGITS
     golf
    0.16
     explicit
    0.15
     Golf
    0.15
    celain
    0.15
    cket
    0.15
    CKET
    0.14
     using
    0.14
    IPLE
    0.14
     explicitly
    0.14
     safer
    0.14
    Activations Density 0.171%

    No Known Activations