© 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 EvalsExportsAPI 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. 14803
    Prev
    Next
    INDEX
    Explanations

    words related to claims or accusations about events or actions

    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
     allegedly
    -0.20
     supposedly
    -0.20
     seemingly
    -0.18
     sanki
    -0.17
     reportedly
    -0.17
     alleged
    -0.17
     apparently
    -0.17
     Alleg
    -0.16
    chy
    -0.15
     Apparently
    -0.15
    POSITIVE LOGITS
    ิà¸ŀ
    0.18
    /misc
    0.16
    ture
    0.14
    ards
    0.14
    OperationException
    0.14
     still
    0.14
     STILL
    0.13
    okay
    0.13
     mots
    0.13
    iaux
    0.13
    Activations Density 0.047%

    No Known Activations