© 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. 55055
    Prev
    Next
    INDEX
    Explanations

    references to downloadable content (DLC) in gaming and mentions of specific players and doping in sports

    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
    ducted
    -0.19
    ж
    -0.17
    .parseFloat
    -0.17
    ammed
    -0.17
    rew
    -0.16
    段
    -0.15
    ALE
    -0.15
    inner
    -0.15
    abei
    -0.15
    rlen
    -0.15
    POSITIVE LOGITS
    weed
    0.19
    =D
    0.19
    ãģªãģĦ
    0.19
    .parseDouble
    0.19
    estic
    0.19
    urnal
    0.18
     olsa
    0.18
    ãģªãģı
    0.17
    /DD
    0.17
    itory
    0.17
    Activations Density 0.239%

    No Known Activations