© 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. 41748
    Prev
    Next
    INDEX
    Explanations

    occurrences 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
    quo
    -0.13
     dostan
    -0.13
    ãĥ³ãĥĩ
    -0.13
    ãĥ³ãĤ¯
    -0.12
    кид
    -0.11
     zas
    -0.11
    jÃŃž
    -0.11
    poÄį
    -0.11
    standing
    -0.11
    bage
    -0.11
    POSITIVE LOGITS
     above
    0.33
    odore
    0.29
     next
    0.24
    odor
    0.23
    oretical
    0.23
    atre
    0.23
    above
    0.22
    orem
    0.22
     lesson
    0.21
    oret
    0.21
    Activations Density 0.690%

    No Known Activations