© 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. 43775
    Prev
    Next
    INDEX
    Explanations

    expressions related to quantity and measurement comparisons

    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
    lest
    -0.16
    ifa
    -0.16
    egin
    -0.16
    Äįel
    -0.16
    est
    -0.14
    aviest
    -0.14
     Canton
    -0.14
    abcdefghijkl
    -0.14
    ActivityIndicatorView
    -0.14
    éļİ
    -0.14
    POSITIVE LOGITS
     greater
    0.26
     higher
    0.23
     larger
    0.22
     more
    0.21
    fold
    0.21
    greater
    0.21
     times
    0.19
    higher
    0.18
     fold
    0.17
     bigger
    0.17
    Activations Density 0.021%

    No Known Activations