© 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. 40606
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to counts

    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
     thousand
    -0.23
     thousands
    -0.22
     Thousand
    -0.17
     thous
    -0.16
     Thousands
    -0.16
    åįĥ
    -0.16
     åįĥ
    -0.16
    Thousands
    -0.15
     millions
    -0.14
    canf
    -0.14
    POSITIVE LOGITS
    50
    0.41
    40
    0.38
    44
    0.37
    49
    0.36
    60
    0.36
    54
    0.35
    64
    0.34
    56
    0.34
    51
    0.34
    53
    0.34
    Activations Density 0.147%

    No Known Activations