© 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. 14837
    Prev
    Next
    INDEX
    Explanations

    requirements and criteria for applicants in competitive events

    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
    _verbose
    -0.17
    icher
    -0.16
    unma
    -0.16
    ÏħÏĩ
    -0.16
    nul
    -0.15
    orest
    -0.15
     might
    -0.14
    spor
    -0.14
    dued
    -0.14
    efon
    -0.13
    POSITIVE LOGITS
     minimum
    0.62
    minimum
    0.49
     Minimum
    0.48
    Minimum
    0.45
    èĩ³å°ij
    0.37
     alespoÅĪ
    0.36
     mÃŃnimo
    0.36
     ØŃداÙĤÙĦ
    0.35
     миним
    0.33
     least
    0.32
    Activations Density 0.060%

    No Known Activations