© 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. 32953
    Prev
    Next
    INDEX
    Explanations

    significant actions or changes in technological advancements

    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
    èģĶç½ij
    -0.16
    OfMonth
    -0.14
    isko
    -0.14
    à¸ĵ
    -0.14
    oire
    -0.13
    ervised
    -0.13
    олÑİ
    -0.13
    yo
    -0.13
     debido
    -0.13
    енÑĮ
    -0.13
    POSITIVE LOGITS
     with
    0.72
    with
    0.57
     avec
    0.52
     vỼi
    0.49
     With
    0.49
     dengan
    0.48
    	with
    0.47
    ewith
    0.44
    With
    0.42
    _with
    0.42
    Activations Density 0.039%

    No Known Activations