© 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. 63737
    Prev
    Next
    INDEX
    Explanations

    prominent names or phrases in contexts related to personal mentions or criticisms

    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
    aqu
    -0.17
     jadx
    -0.14
    Aqu
    -0.14
    ali
    -0.14
    acios
    -0.13
    alsex
    -0.13
    udeau
    -0.13
     Aqu
    -0.13
    romium
    -0.13
    íħ
    -0.13
    POSITIVE LOGITS
     AM
    0.79
    AM
    0.71
     am
    0.66
     Amb
    0.63
    .am
    0.63
    amb
    0.61
    _am
    0.61
    am
    0.60
    Am
    0.60
     ам
    0.59
    Activations Density 0.007%

    No Known Activations