© 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. 44937
    Prev
    Next
    INDEX
    Explanations

    references to transit systems and legal issues related to sports

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    iras
    -0.15
    rophe
    -0.14
    otron
    -0.13
    otti
    -0.13
    plet
    -0.13
     repl
    -0.13
    ettel
    -0.13
    e
    -0.13
    erca
    -0.12
    *
    -0.12
    POSITIVE LOGITS
     pic
    0.55
     https
    0.46
    pic
    0.41
    https
    0.38
     #
    0.38
     http
    0.34
    .pic
    0.33
     @
    0.33
     Pic
    0.32
    -pic
    0.31
    Activations Density 0.066%

    No Known Activations