© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41360
    Prev
    Next
    INDEX
    Explanations

    references to public input and comments on legislative matters

    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
    ouri
    -0.19
     awakeFromNib
    -0.14
     cánh
    -0.14
    ád
    -0.14
    PIX
    -0.14
    els
    -0.13
    ORIZ
    -0.13
    ekl
    -0.13
    è¨ĺäºĭ
    -0.13
    heed
    -0.13
    POSITIVE LOGITS
     comments
    0.35
     comment
    0.34
     input
    0.30
     Comments
    0.29
    comments
    0.28
    Comments
    0.27
    -comment
    0.27
    comment
    0.26
     inputs
    0.26
     COMMENTS
    0.26
    Activations Density 0.029%

    No Known Activations