© 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. 15815
    Prev
    Next
    INDEX
    Explanations

    medical terms related to injuries and surgeries

    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
    /apis
    -0.14
    ansı
    -0.14
     UCHAR
    -0.14
    éģ£
    -0.14
    -inf
    -0.13
    éı
    -0.13
    LAS
    -0.13
    _PARAMS
    -0.13
     buff
    -0.13
    件
    -0.13
    POSITIVE LOGITS
    icular
    0.27
    /test
    0.19
     test
    0.18
    icle
    0.17
    /Test
    0.17
    osterone
    0.17
     Germ
    0.17
    çĿ
    0.17
     germ
    0.16
     Ley
    0.16
    Activations Density 0.004%

    No Known Activations