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

    Neuronpedia

    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. 15118
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or obligation

    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
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.17
    edException
    -0.16
    ernote
    -0.16
    Ìĥ
    -0.15
     Decoration
    -0.15
    dorf
    -0.14
    leyen
    -0.14
    apg
    -0.14
    VERRIDE
    -0.14
    mur
    -0.14
    POSITIVE LOGITS
     do
    0.39
     with
    0.38
    with
    0.28
     vỼi
    0.28
     With
    0.26
     avec
    0.25
    	with
    0.23
    With
    0.23
     dengan
    0.23
     Do
    0.23
    Activations Density 0.013%

    No Known Activations