© 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. 21149
    Prev
    Next
    INDEX
    Explanations

    the use of the word "to" 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
    inia
    -0.20
    inine
    -0.17
    kol
    -0.17
    abar
    -0.16
     eldre
    -0.15
    .TestTools
    -0.15
    ll
    -0.14
    noon
    -0.14
    Ïĥια
    -0.14
    uste
    -0.14
    POSITIVE LOGITS
     extent
    0.44
     varying
    0.41
     extents
    0.36
     degree
    0.33
    extent
    0.32
     degrees
    0.30
    Extent
    0.26
     Degree
    0.26
    degree
    0.25
    vary
    0.25
    Activations Density 0.041%

    No Known Activations