© 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. 26184
    Prev
    Next
    INDEX
    Explanations

    terms related to animation techniques and software used in film production

    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
     photographic
    -0.19
     fotograf
    -0.17
     Photographer
    -0.17
     Photograph
    -0.16
    åĨĻ羣
    -0.16
     photograph
    -0.16
     photographs
    -0.15
     selfie
    -0.15
     selfies
    -0.15
     photographer
    -0.15
    POSITIVE LOGITS
     animation
    0.88
     anim
    0.83
     Animation
    0.78
     animated
    0.76
     animations
    0.69
     animator
    0.68
     Anim
    0.67
     animate
    0.66
    animation
    0.65
    Animation
    0.65
    Activations Density 0.045%

    No Known Activations