© 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. 21584
    Prev
    Next
    INDEX
    Explanations

    the word "ch" and its variations

    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
    arak
    -0.17
    chap
    -0.17
    itud
    -0.16
    aro
    -0.16
    bis
    -0.15
    arro
    -0.15
    allest
    -0.15
    abbr
    -0.15
    ARA
    -0.15
    Ïģαβ
    -0.14
    POSITIVE LOGITS
     ch
    0.34
    urning
    0.17
    thon
    0.17
    EAR
    0.17
    ipping
    0.17
    lam
    0.16
    lord
    0.16
     Advance
    0.16
    ican
    0.16
    oral
    0.16
    Activations Density 0.011%

    No Known Activations