© 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. 15166
    Prev
    Next
    INDEX
    Explanations

    references to circus performers and associated artistic themes

    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
    unik
    -0.15
    ehler
    -0.15
    ÑĤаж
    -0.15
    ạch
    -0.15
    apons
    -0.14
    _observer
    -0.14
    θÏħ
    -0.14
    èĩªæĭį
    -0.14
     rencont
    -0.14
     CACHE
    -0.13
    POSITIVE LOGITS
     circ
    0.45
     circus
    0.40
    circ
    0.36
     Circus
    0.35
     Cir
    0.33
     Circ
    0.32
     sides
    0.31
     va
    0.30
     cir
    0.29
     performers
    0.29
    Activations Density 0.043%

    No Known Activations