© 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. 29762
    Prev
    Next
    INDEX
    Explanations

    instances or examples of situations and events

    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
     these
    -0.27
     this
    -0.26
    this
    -0.21
    éĢĻ
    -0.20
    è¿ĻäºĽ
    -0.19
    ãģĵãģ®
    -0.18
     THESE
    -0.18
     other
    -0.17
    these
    -0.17
     These
    -0.17
    POSITIVE LOGITS
     if
    0.34
     when
    0.33
    when
    0.31
     If
    0.28
    If
    0.26
     during
    0.26
     еÑģли
    0.26
     When
    0.26
    å¦Ĥæŀľ
    0.25
     wenn
    0.25
    Activations Density 0.043%

    No Known Activations