© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 28539
    Prev
    Next
    INDEX
    Explanations

    references to technical terms and frameworks related to technology and infrastructure

    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
     koji
    -0.35
    “He
    -0.34
    "He
    -0.34
     Ñıкий
    -0.30
     коÑĤоÑĢÑĭй
    -0.28
     italiano
    -0.28
     který
    -0.28
     stesso
    -0.26
     اÙĦجدÙĬد
    -0.25
     celui
    -0.24
    POSITIVE LOGITS
    “She
    0.59
    "She
    0.56
     herself
    0.48
     коÑĤоÑĢаÑı
    0.43
     która
    0.39
     коÑĤоÑĢÑĥÑİ
    0.39
     αÏħÏĦή
    0.37
     italiana
    0.36
     která
    0.33
     kterou
    0.32
    Activations Density 0.021%

    No Known Activations