© 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. 21308
    Prev
    Next
    INDEX
    Explanations

    phrases related to eligibility criteria in various contexts

    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
    تÙĨ
    -0.15
    inke
    -0.14
    izzo
    -0.14
    aldi
    -0.14
    ål
    -0.13
    estro
    -0.13
    omy
    -0.13
    Estimated
    -0.13
    Æ¡n
    -0.13
    lettes
    -0.12
    POSITIVE LOGITS
     criteria
    0.83
     Criteria
    0.69
     criterion
    0.65
    criteria
    0.64
    Criteria
    0.63
     criter
    0.56
     Criterion
    0.56
    _criteria
    0.55
    Criterion
    0.51
    .criteria
    0.48
    Activations Density 0.060%

    No Known Activations