© 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. 14576
    Prev
    Next
    INDEX
    Explanations

    words and concepts related to inequality and social justice

    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
     voksne
    -0.15
    OLON
    -0.15
    zig
    -0.14
     MERCHANTABILITY
    -0.14
    tridge
    -0.14
    oley
    -0.14
    ettings
    -0.14
     GENERATED
    -0.14
    ÙĪÙĬر
    -0.14
     PROVIDED
    -0.14
    POSITIVE LOGITS
     suddenly
    0.32
     evapor
    0.29
     has
    0.28
     gone
    0.26
     van
    0.24
     now
    0.22
     zosta
    0.22
     abruptly
    0.22
     Gone
    0.22
     Suddenly
    0.22
    Activations Density 0.133%

    No Known Activations