© 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 EvalsExportsinterp-engineNEWAPI 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. 43898
    Prev
    Next
    INDEX
    Explanations

    phrases related to transformation and size change

    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
    orsch
    -0.13
    opot
    -0.12
    pageNumber
    -0.12
    олева
    -0.12
    åİļ
    -0.12
    mey
    -0.12
    lements
    -0.12
    ÙĩÙĨ
    -0.11
    ë¹ĦìĬ¤
    -0.11
    elere
    -0.11
    POSITIVE LOGITS
     small
    1.18
     Small
    1.02
     smaller
    1.02
    small
    1.02
     SMALL
    0.99
    Small
    0.95
     tiny
    0.92
    -small
    0.90
    å°ı
    0.87
     smallest
    0.85
    Activations Density 0.025%

    No Known Activations