© 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. 44933
    Prev
    Next
    INDEX
    Explanations

    concepts related to amusement park rides and technology patents

    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
    ovo
    -0.14
    //{{
    -0.14
    нок
    -0.14
    asal
    -0.14
    нож
    -0.13
    инÑĥ
    -0.13
    _proba
    -0.13
     uvol
    -0.13
    çĤ¸
    -0.13
    .generated
    -0.12
    POSITIVE LOGITS
     theme
    0.54
     Theme
    0.47
     park
    0.44
    Theme
    0.43
     attractions
    0.42
     attraction
    0.41
     amusement
    0.40
     THEME
    0.37
    theme
    0.36
     themed
    0.36
    Activations Density 0.020%

    No Known Activations