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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12714
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and relationships

    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
     ↵↵
    -0.16
     kå
    -0.15
    å¤ļãģĦ
    -0.15
    cházÃŃ
    -0.14
    ibold
    -0.14
    ãģĦãĤĭ
    -0.14
    asename
    -0.14
    readcr
    -0.14
    —is
    -0.14
    ĵĺ
    -0.14
    POSITIVE LOGITS
     had
    0.83
     hadn
    0.71
    had
    0.69
    Had
    0.59
     habÃŃa
    0.58
     Had
    0.54
     hade
    0.51
     avait
    0.50
     hatte
    0.49
     hadde
    0.48
    Activations Density 0.211%

    No Known Activations