© 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. 8916
    Prev
    Next
    INDEX
    Explanations

    phrases related to the capabilities and operations of services or organizations

    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
    à¹ģà¸ķ
    -0.15
    Ø°
    -0.15
    /Form
    -0.15
    ecome
    -0.15
    deÅŁ
    -0.14
    iez
    -0.14
    åĿĬ
    -0.14
    cü
    -0.13
    ereg
    -0.13
    çľĭçľĭ
    -0.13
    POSITIVE LOGITS
     function
    0.29
     effectively
    0.23
    function
    0.23
     adequately
    0.23
     properly
    0.21
     conduct
    0.20
     functioning
    0.20
     continue
    0.20
     Function
    0.20
     effective
    0.20
    Activations Density 0.161%

    No Known Activations