© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 55232
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and personal connections

    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
    “She
    -0.39
     heroine
    -0.38
     sisters
    -0.38
    daughter
    -0.38
     actresses
    -0.37
    "She
    -0.37
     daughters
    -0.36
     daughter
    -0.36
     women
    -0.35
     woman
    -0.35
    POSITIVE LOGITS
     boy
    0.64
    boy
    0.55
     son
    0.55
     Boy
    0.54
    -boy
    0.52
    Boy
    0.52
     boys
    0.51
     Boys
    0.48
    boys
    0.44
     sons
    0.43
    Activations Density 0.018%

    No Known Activations