© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29639
    Prev
    Next
    INDEX
    Explanations

    symbols or special characters indicating formatting issues or corrupted text

    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
    ways
    -0.16
    onian
    -0.16
    otle
    -0.15
    ÃĹ↵↵
    -0.15
    PIX
    -0.15
    BTC
    -0.15
    га
    -0.15
    wards
    -0.15
    eck
    -0.14
    .Selenium
    -0.14
    POSITIVE LOGITS
    ï¸
    0.18
    ¦
    0.16
    agraph
    0.16
    ifications
    0.16
    ï¸ı
    0.15
    cket
    0.15
    quares
    0.15
    peg
    0.15
    _tid
    0.15
    _HERSHEY
    0.14
    Activations Density 0.005%

    No Known Activations