© 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. 45266
    Prev
    Next
    INDEX
    Explanations

    specific relationships and interactions among people

    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
    -0.27
     Himself
    -0.20
     jeho
    -0.20
     his
    -0.20
    ä»ĸçļĦ
    -0.20
     jego
    -0.19
     Ø®ÙĪدش
    -0.17
    His
    -0.17
    his
    -0.17
     kendisi
    -0.17
    POSITIVE LOGITS
     together
    0.54
     respectively
    0.52
     respective
    0.49
     themselves
    0.49
     their
    0.43
     mutual
    0.42
     joint
    0.41
     Together
    0.41
     alike
    0.40
     nhau
    0.40
    Activations Density 0.055%

    No Known Activations