© 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. 14661
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating relationships or connections between entities

    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
    aston
    -0.15
    aternity
    -0.14
     danmark
    -0.14
    iferay
    -0.14
     Verfüg
    -0.14
    /renderer
    -0.14
    лага
    -0.14
    ÏģÏħ
    -0.13
    LOUR
    -0.13
    (éĩij
    -0.13
    POSITIVE LOGITS
     existing
    0.54
     current
    0.45
     Existing
    0.43
    existing
    0.41
    Existing
    0.38
    current
    0.36
    -existing
    0.36
     new
    0.34
     former
    0.34
     newer
    0.33
    Activations Density 0.033%

    No Known Activations