© 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. 54992
    Prev
    Next
    INDEX
    Explanations

    references to single-payer health care systems

    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
    soever
    -0.19
    etten
    -0.17
    ãĥ³ãĤ¿
    -0.17
    ppers
    -0.15
    nas
    -0.15
    erk
    -0.14
    اÙģÙĤ
    -0.14
    eÅŁit
    -0.14
    edImage
    -0.14
    rer
    -0.14
    POSITIVE LOGITS
    tons
    0.43
    /single
    0.33
    -handed
    0.28
    (single
    0.27
    -minded
    0.26
    ChildScrollView
    0.26
    -single
    0.25
     handed
    0.25
     malt
    0.24
    TON
    0.24
    Activations Density 0.017%

    No Known Activations