© 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. 24802
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "in" across various contexts

    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
     Partial
    -0.16
    ulla
    -0.14
    etic
    -0.14
    Partial
    -0.13
    ouz
    -0.13
    è®
    -0.13
     Affairs
    -0.13
    뮤
    -0.13
    ypical
    -0.13
    sofar
    -0.13
    POSITIVE LOGITS
     general
    0.68
    general
    0.53
     generally
    0.51
     geral
    0.49
     général
    0.47
    -general
    0.45
     overall
    0.44
    gener
    0.41
     genel
    0.41
     Generally
    0.39
    Activations Density 0.021%

    No Known Activations