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. 15973
    Prev
    Next
    INDEX
    Explanations

    scientific terms and measurements related to peptides and serum analysis

    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
    pie
    -0.15
    umba
    -0.14
    sse
    -0.14
     Burning
    -0.14
    æ°§
    -0.13
     èĬ
    -0.13
    [
    -0.13
    å¸Ń
    -0.13
     pie
    -0.13
    bane
    -0.13
    POSITIVE LOGITS
     solution
    0.24
     solutions
    0.23
     Solutions
    0.22
    solution
    0.21
     PBS
    0.21
    PBS
    0.20
     stock
    0.20
     culture
    0.20
    Solution
    0.19
    _solution
    0.19
    Activations Density 0.014%

    No Known Activations