© 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. 22576
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" and its context within sentences regarding various subjects

    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
     same
    -0.22
     several
    -0.19
     which
    -0.17
     Same
    -0.17
     another
    -0.16
    Same
    -0.16
     whom
    -0.16
     something
    -0.15
    arend
    -0.15
     Several
    -0.15
    POSITIVE LOGITS
     these
    0.22
     each
    0.20
    these
    0.19
     those
    0.19
    those
    0.17
     during
    0.17
    åIJĦ
    0.17
    each
    0.17
    éĤ£äºĽ
    0.17
    Each
    0.17
    Activations Density 0.043%

    No Known Activations