© 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. 14412
    Prev
    Next
    INDEX
    Explanations

    expressions of refusal or negation

    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
    nesc
    -0.16
    land
    -0.14
    bew
    -0.14
    gaard
    -0.14
    Ãłnh
    -0.13
    nga
    -0.13
    orrh
    -0.13
    apos
    -0.13
    adge
    -0.13
    sto
    -0.13
    POSITIVE LOGITS
    pe
    0.39
     way
    0.29
     WAY
    0.28
     sir
    0.26
     Way
    0.26
    PE
    0.22
    thin
    0.21
    -way
    0.21
     offense
    0.20
    _way
    0.20
    Activations Density 0.035%

    No Known Activations