© 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 EvalsExportsinterp-engineNEWAPI 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. 13073
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to societal issues

    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
    -0.19
     (*((
    -0.16
    0
    -0.16
    00
    -0.16
    寸
    -0.15
     /
    -0.15
    08
    -0.15
     fe
    -0.15
    01
    -0.14
    09
    -0.14
    POSITIVE LOGITS
     à¤¹à¤ľ
    0.20
     tens
    0.17
    Ư
    0.16
     thousands
    0.16
     THROW
    0.16
     ~(
    0.15
     hundreds
    0.15
    ubat
    0.15
    udu
    0.14
    -www
    0.14
    Activations Density 1.654%

    No Known Activations