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

    Neuronpedia

    Jacobian LensNEW
    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. 14394
    Prev
    Next
    INDEX
    Explanations

    expressions of skepticism or refusal towards claims or offers

    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
    OrDefault
    -0.16
    íĭĢ
    -0.15
    rze
    -0.15
    zych
    -0.14
     centerX
    -0.14
    ugg
    -0.14
    oje
    -0.13
     strncmp
    -0.13
    ãģłãģ£ãģ¦
    -0.13
    iton
    -0.13
    POSITIVE LOGITS
     buying
    0.34
     buy
    0.34
    buy
    0.32
    Buy
    0.28
     Buy
    0.28
    Buying
    0.27
     Buying
    0.27
     buys
    0.27
     bought
    0.27
    -buy
    0.26
    Activations Density 0.019%

    No Known Activations