© 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. 14041
    Prev
    Next
    INDEX
    Explanations

    unique or special characters, particularly in a coded or formatted 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
    InSection
    -0.16
    ston
    -0.15
    leyen
    -0.15
    .MixedReality
    -0.15
    /stretch
    -0.15
     Scre
    -0.15
    /slider
    -0.15
    /slick
    -0.14
    urger
    -0.14
     Saul
    -0.14
    POSITIVE LOGITS
     Sh
    0.56
    Sh
    0.52
     sh
    0.49
    _sh
    0.48
     Ш
    0.46
    -sh
    0.46
     SH
    0.43
     श
    0.41
    -Sh
    0.41
    sh
    0.40
    Activations Density 0.025%

    No Known Activations