© 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. 26190
    Prev
    Next
    INDEX
    Explanations

    terms related to large quantities or volumes

    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
    ivate
    -0.21
    ivism
    -0.19
    àµį
    -0.17
    /stdc
    -0.17
    agar
    -0.15
    ÑģÑĥÑĤ
    -0.15
    าà¸ķร
    -0.15
    .gwt
    -0.15
    bai
    -0.15
    zeit
    -0.15
    POSITIVE LOGITS
    bers
    0.24
    bed
    0.22
    pton
    0.22
    etric
    0.22
    ptive
    0.22
    inal
    0.22
    inate
    0.21
    t
    0.21
    ption
    0.21
    ycin
    0.19
    Activations Density 0.024%

    No Known Activations