© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 63340
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" in 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
    vr
    -0.17
    resher
    -0.15
    iT
    -0.15
    idal
    -0.15
    eview
    -0.14
    anford
    -0.14
     ä½Ľ
    -0.14
    rish
    -0.14
    ouz
    -0.14
    scribe
    -0.14
    POSITIVE LOGITS
    ARAM
    0.15
    ót
    0.15
    uess
    0.15
     done
    0.15
     clin
    0.14
    orious
    0.14
    occasion
    0.14
     alone
    0.14
     ÄĮer
    0.14
    HEMA
    0.14
    Activations Density 0.035%

    No Known Activations