© 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. 45277
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their relationships or roles

    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
     himself
    -0.35
     fathers
    -0.29
     Fathers
    -0.28
     Father
    -0.27
     grandfather
    -0.27
     gentleman
    -0.27
     guy
    -0.26
    Father
    -0.26
     boy
    -0.26
     handsome
    -0.25
    POSITIVE LOGITS
     herself
    0.58
     daughter
    0.41
    “She
    0.40
    "She
    0.39
     mother
    0.38
    daughter
    0.36
     sister
    0.34
     goddess
    0.32
     woman
    0.32
     коÑĤоÑĢаÑı
    0.31
    Activations Density 0.093%

    No Known Activations