© 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. 22457
    Prev
    Next
    INDEX
    Explanations

    terms related to openings and establishments of services or facilities

    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
    anford
    -0.15
    ÑĢап
    -0.13
    ĵåIJį
    -0.13
    kova
    -0.13
    alink
    -0.13
    igest
    -0.13
     Clarkson
    -0.13
    adlo
    -0.13
    ัม
    -0.13
    åij¼ãģ°
    -0.13
    POSITIVE LOGITS
     opening
    1.27
     opened
    1.13
     Opening
    1.07
    opening
    1.07
    Opening
    1.06
     opens
    1.06
    -opening
    1.04
     openings
    1.04
    opened
    0.97
     Opens
    0.90
    Activations Density 0.020%

    No Known Activations