© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 42971
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions and geographical locations

    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
    âĢ¦↵
    -0.21
     âĢ¦↵
    -0.17
     [âĢ¦]↵
    -0.15
    ..↵
    -0.14
     (
    -0.14
    ...↵
    -0.14
    âĢ¦↵↵
    -0.14
    Âłin
    -0.14
    âĢ¦
    -0.14
    Âł
    -0.13
    POSITIVE LOGITS
    _OW
    0.13
    سÙħØ©
    0.13
    ëį°ìĿ´íĬ¸
    0.13
    ñana
    0.12
     اختÙĦ
    0.12
    ÃĹ↵↵
    0.12
    ï¼Ĭ
    0.12
     acomp
    0.12
     Ñģигн
    0.12
    Äł
    0.12
    Activations Density 1.237%

    No Known Activations