© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 32933
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the."

    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
    ãĥ³ãĥIJ
    -0.16
     недел
    -0.14
    omen
    -0.14
    illin
    -0.13
    LOAT
    -0.13
    ël
    -0.13
    éłĥ
    -0.13
    enstein
    -0.13
    ILLS
    -0.13
    answered
    -0.13
    POSITIVE LOGITS
     help
    0.44
     exception
    0.37
     aid
    0.35
     assistance
    0.30
     intention
    0.28
     aim
    0.28
    help
    0.27
     added
    0.27
     caveat
    0.27
     intent
    0.26
    Activations Density 0.073%

    No Known Activations