© 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. 54506
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions and decision-making phrases

    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
     Sort
    -0.16
    tuÄŁ
    -0.14
    ongan
    -0.14
    ept
    -0.14
     sourceMapping
    -0.14
    ãģĭ
    -0.13
    echan
    -0.13
    å®ħ
    -0.13
    ãģªãģĮãĤī
    -0.13
    ัà¸Ļว
    -0.13
    POSITIVE LOGITS
     which
    1.08
     Which
    0.99
    which
    0.91
    Which
    0.89
     WHICH
    0.87
    .which
    0.65
    åĵª
    0.65
     wich
    0.62
     cuales
    0.58
     które
    0.54
    Activations Density 0.023%

    No Known Activations