Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23218
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "secret" 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
    eled
    -0.15
    tures
    -0.15
    ales
    -0.15
    qv
    -0.14
    ole
    -0.14
     Honest
    -0.14
    ket
    -0.14
    kers
    -0.14
    hip
    -0.13
    ilet
    -0.13
    POSITIVE LOGITS
     secret
    0.30
     ingredient
    0.29
    iveness
    0.28
    arial
    0.27
    (secret
    0.25
    ariat
    0.25
    secret
    0.24
     sauce
    0.24
     Ingredient
    0.24
    ive
    0.23
    Activations Density 0.013%

    No Known Activations