© 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. 28926
    Prev
    Next
    INDEX
    Explanations

    terms related to soft and pneumatic robotics

    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
     sme
    -0.14
     drip
    -0.14
    าà¸į
    -0.14
     Geh
    -0.14
    klad
    -0.14
     smear
    -0.14
    eneric
    -0.14
    amel
    -0.13
    olik
    -0.13
    ằm
    -0.13
    POSITIVE LOGITS
    inflate
    0.46
     inflate
    0.46
     inflation
    0.45
     Inflate
    0.43
     deflate
    0.42
     inflated
    0.41
     infl
    0.36
    flate
    0.35
     pressure
    0.34
    flation
    0.34
    Activations Density 0.016%

    No Known Activations