© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12424
    Prev
    Next
    INDEX
    Explanations

    references to key characters and specific actions related to custody and coordination in a narrative context

    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
     ifndef
    -0.14
    .GetData
    -0.13
     gangbang
    -0.13
         č↵
    -0.13
    å¡ļ
    -0.13
    _NPC
    -0.12
    (Have
    -0.12
     Leban
    -0.12
     Singap
    -0.12
    Âłtom
    -0.11
    POSITIVE LOGITS
     destinationViewController
    0.16
     eskort
    0.15
    .fromFunction
    0.14
    ..↵
    0.13
    .SizeType
    0.13
     kå
    0.13
    .Undef
    0.13
     wireType
    0.13
    W
    0.13
    .updateDynamic
    0.13
    Activations Density 0.055%

    No Known Activations