© 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. 12154
    Prev
    Next
    INDEX
    Explanations

    cooking methods related to food preparation

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    lei
    -0.19
    antly
    -0.15
    brew
    -0.15
    alth
    -0.15
    ages
    -0.15
     Bake
    -0.14
    pace
    -0.14
    athed
    -0.14
    boat
    -0.14
     Pie
    -0.14
    POSITIVE LOGITS
     GOODS
    0.20
     chicken
    0.19
     Goods
    0.19
     goods
    0.18
    onz
    0.16
     Spam
    0.16
    Cod
    0.15
     foods
    0.15
     Crane
    0.15
     meats
    0.15
    Activations Density 0.030%

    No Known Activations