© 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. 41301
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or regulatory concepts

    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
     probably
    -0.29
     basically
    -0.24
    probably
    -0.23
     Probably
    -0.21
     likely
    -0.20
    Probably
    -0.20
     surely
    -0.19
    èĤ¯å®ļ
    -0.19
    åŁºæľ¬
    -0.19
     essentially
    -0.17
    POSITIVE LOGITS
     slightly
    0.28
     some
    0.24
     someday
    0.23
     algún
    0.22
     depending
    0.21
     qualche
    0.21
     algun
    0.21
    some
    0.20
     SOME
    0.19
    ä¸ĢäºĽ
    0.19
    Activations Density 0.100%

    No Known Activations