© 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. 33490
    Prev
    Next
    INDEX
    Explanations

    references to unions and endorsements in a political context

    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
    alue
    -0.19
    ãĤ¹ãĥĿ
    -0.15
    ίλ
    -0.15
    cheid
    -0.14
    nia
    -0.14
    ertino
    -0.14
     jadx
    -0.14
    quet
    -0.14
    ynchronously
    -0.14
    actus
    -0.14
    POSITIVE LOGITS
     union
    1.01
     unions
    0.87
     Union
    0.83
    union
    0.82
    Union
    0.74
     UNION
    0.72
    _union
    0.62
    .union
    0.58
    	union
    0.56
     labor
    0.45
    Activations Density 0.056%

    No Known Activations