© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8448
    Prev
    Next
    INDEX
    Explanations

    phrases related to race and socioeconomic status inequality

    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
    elman
    -0.17
    -alist
    -0.15
    reten
    -0.15
    Äħd
    -0.15
    orum
    -0.15
    Äĥn
    -0.14
    breadcrumb
    -0.13
    intree
    -0.13
    ipy
    -0.13
    à¹īà¸Ń
    -0.13
    POSITIVE LOGITS
     white
    0.89
    white
    0.79
     White
    0.69
     whites
    0.69
     WHITE
    0.69
    çĻ½
    0.68
    -white
    0.68
    White
    0.66
    WHITE
    0.62
    _white
    0.61
    Activations Density 0.149%

    No Known Activations