© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 30228
    Prev
    Next
    INDEX
    Explanations

    phrases related to government financial institutions and economic policies

    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
    undy
    -0.17
     compens
    -0.15
     wages
    -0.14
     enrich
    -0.14
     Trim
    -0.14
    399
    -0.14
     teenage
    -0.14
     emo
    -0.14
    ices
    -0.14
    ÂĽ
    -0.14
    POSITIVE LOGITS
     guarantees
    0.21
     guarantee
    0.20
     financ
    0.19
    fin
    0.19
     Mobil
    0.19
     sovereign
    0.18
    xic
    0.18
     Guarantee
    0.18
     concess
    0.18
    callable
    0.17
    Activations Density 0.025%

    No Known Activations