© 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 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. 28160
    Prev
    Next
    INDEX
    Explanations

    phrases related to guidelines or recommendations concerning usage and categorization

    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
    robe
    -0.15
    ÑģÑĤвоÑĢ
    -0.14
    ipa
    -0.14
    vig
    -0.14
    ÏģÏİ
    -0.14
    redo
    -0.13
    ncoder
    -0.13
    Įĵ
    -0.13
    abbo
    -0.13
    .userInteractionEnabled
    -0.13
    POSITIVE LOGITS
     purposes
    0.96
     Pur
    0.87
    pur
    0.84
     purpose
    0.82
     pur
    0.80
     PURPOSE
    0.66
     Purpose
    0.65
    purpose
    0.64
    Purpose
    0.62
    PUR
    0.60
    Activations Density 0.045%

    No Known Activations