© 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. 14144
    Prev
    Next
    INDEX
    Explanations

    descriptive statements related to food preparation

    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
     hardly
    -0.23
     not
    -0.21
     deÄŁil
    -0.20
     no
    -0.20
     nicht
    -0.20
     não
    -0.19
     tidak
    -0.19
    ä¸įæĺ¯
    -0.18
    à¹Ħม
    -0.18
     không
    -0.17
    POSITIVE LOGITS
     purely
    0.29
     pure
    0.27
    ç´Ķ
    0.27
    pure
    0.27
    纯
    0.26
     solely
    0.24
     PURE
    0.23
     strictly
    0.23
     simply
    0.23
    Pure
    0.23
    Activations Density 0.024%

    No Known Activations