© 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. 30602
    Prev
    Next
    INDEX
    Explanations

    references to the concept of economic theory or ideology

    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
    edin
    -0.17
    stial
    -0.15
    .handlers
    -0.15
    lein
    -0.15
    iku
    -0.14
    arin
    -0.14
     ãĢĥ
    -0.14
    ACHI
    -0.14
    æ¬ł
    -0.14
    (Page
    -0.14
    POSITIVE LOGITS
    boo
    0.16
    cape
    0.16
    ubar
    0.16
    udem
    0.15
    metics
    0.15
    umor
    0.15
    thon
    0.15
     Nes
    0.15
    iac
    0.14
     Clown
    0.14
    Activations Density 0.008%

    No Known Activations