© 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. 32999
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and their management through cannabis

    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
     Cov
    -0.16
    ubber
    -0.15
    gne
    -0.15
     ldc
    -0.15
    pagen
    -0.14
     bes
    -0.14
    ìĿ´ìĸ´
    -0.14
    xic
    -0.14
    abbage
    -0.14
     saturated
    -0.14
    POSITIVE LOGITS
     pain
    0.27
     Pain
    0.22
     seizure
    0.21
    pain
    0.21
     seizures
    0.21
     Fib
    0.21
     pains
    0.21
     fib
    0.19
     migr
    0.18
    chron
    0.18
    Activations Density 0.020%

    No Known Activations