© 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. 23876
    Prev
    Next
    INDEX
    Explanations

    concepts and issues related to cost and resource management

    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
    unca
    -0.13
     while
    -0.13
     anywhere
    -0.13
    orgia
    -0.13
     tháºŃm
    -0.12
    zon
    -0.12
    linky
    -0.12
    eza
    -0.12
     nor
    -0.12
    £½
    -0.12
    POSITIVE LOGITS
     itself
    0.36
     aspect
    0.33
    aspect
    0.28
     Aspect
    0.26
    Aspect
    0.26
    æĸ¹éĿ¢
    0.26
     alone
    0.23
     aspects
    0.22
     samot
    0.20
     issue
    0.20
    Activations Density 0.067%

    No Known Activations