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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 2529
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'q' 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
    u
    -0.24
    t
    -0.18
    uw
    -0.18
    uju
    -0.18
    uv
    -0.17
    uz
    -0.17
    uh
    -0.17
    iker
    -0.17
    uin
    -0.17
    aday
    -0.17
    POSITIVE LOGITS
    ubits
    0.32
    ubit
    0.29
    eu
    0.25
    naires
    0.23
    uries
    0.22
    rcode
    0.21
    eur
    0.21
    oS
    0.21
    ele
    0.20
    ä¼į
    0.20
    Activations Density 0.036%

    No Known Activations