© 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. 12270
    Prev
    Next
    INDEX
    Explanations

    references to character development and personal struggles in narratives

    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
    pong
    -0.16
    llib
    -0.15
    amework
    -0.15
     remake
    -0.15
    VERR
    -0.15
    ãĤīãģļ
    -0.15
    jeme
    -0.14
    eful
    -0.14
     springfox
    -0.14
    ราย
    -0.14
    POSITIVE LOGITS
     scenes
    0.20
     emo
    0.18
     exposition
    0.18
     Season
    0.18
     civilian
    0.18
     bro
    0.17
     eps
    0.17
     finally
    0.17
     scene
    0.17
     dealing
    0.16
    Activations Density 0.074%

    No Known Activations