© 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. 24785
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and settings

    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
    .scalablytyped
    -0.16
    åĪ·
    -0.16
    _android
    -0.15
    baru
    -0.14
    atoon
    -0.14
    ê°¤
    -0.14
    éĻ¢
    -0.14
    kara
    -0.14
     SelectList
    -0.14
    HeaderCode
    -0.14
    POSITIVE LOGITS
     desk
    0.62
     Desk
    0.57
     desks
    0.50
    Desk
    0.49
    desk
    0.49
    -des
    0.46
     desktop
    0.44
     DES
    0.41
     Desktop
    0.40
    _des
    0.40
    Activations Density 0.014%

    No Known Activations