© 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. 22573
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and the word "the."

    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
    SingleOrDefault
    -0.18
     {{--<
    -0.13
    ãĤ¦ãĤ©
    -0.13
     Haskell
    -0.13
    HasBeen
    -0.13
    -_
    -0.12
    ยà¸Ńà¸Ķ
    -0.12
    _DX
    -0.12
     Wid
    -0.12
    ispens
    -0.12
    POSITIVE LOGITS
     large
    0.38
    large
    0.31
     LARGE
    0.28
     substantial
    0.26
    Large
    0.26
     sizable
    0.25
     huge
    0.25
    -large
    0.25
     considerable
    0.24
     duż
    0.23
    Activations Density 0.059%

    No Known Activations