© 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. 24032
    Prev
    Next
    INDEX
    Explanations

    descriptions of employment practices and issues related to job security

    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
    sand
    -0.14
    bolt
    -0.14
     income
    -0.14
    boxed
    -0.14
    monthly
    -0.13
    plural
    -0.13
    ajas
    -0.13
     tar
    -0.13
    erator
    -0.13
    olicit
    -0.13
    POSITIVE LOGITS
     hire
    0.32
     Hire
    0.30
     hiring
    0.29
     hires
    0.26
     Hiring
    0.25
     firing
    0.25
     paying
    0.24
    hire
    0.24
     hired
    0.23
     pay
    0.21
    Activations Density 0.043%

    No Known Activations