© 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. 26209
    Prev
    Next
    INDEX
    Explanations

    statements about occupations and their complexity or appeal

    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
    rlen
    -0.14
    urr
    -0.14
    _refl
    -0.14
    _rc
    -0.14
     func
    -0.14
     stores
    -0.13
    CommandEvent
    -0.13
    AGMA
    -0.13
     functioning
    -0.13
    unused
    -0.13
    POSITIVE LOGITS
     demanding
    0.29
     thank
    0.23
     manual
    0.23
     glamour
    0.22
     Reward
    0.22
    -demand
    0.22
     physically
    0.22
     rewarding
    0.21
     demand
    0.21
     Manual
    0.21
    Activations Density 0.054%

    No Known Activations