© 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. 14795
    Prev
    Next
    INDEX
    Explanations

    references to weight and measurements related to objects, particularly in the context of scientific or technical descriptions

    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
    кÑĥÑģ
    -0.15
    /***/
    -0.15
     Xuân
    -0.15
    _DX
    -0.14
    burger
    -0.14
    uffman
    -0.14
    ahren
    -0.14
    _bindings
    -0.14
    à¹ģà¸ģ
    -0.13
    arsing
    -0.13
    POSITIVE LOGITS
     ton
    0.56
     tons
    0.48
    ton
    0.48
     Ton
    0.47
    -ton
    0.45
    Ton
    0.45
    TON
    0.39
     tonnes
    0.38
    tons
    0.36
     tones
    0.35
    Activations Density 0.014%

    No Known Activations