© 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. 8799
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility or necessity

    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
     itself
    -0.23
     its
    -0.23
     Its
    -0.21
    Its
    -0.19
     à¤īसà¤ķ
    -0.17
     kendini
    -0.17
     myself
    -0.17
     himself
    -0.16
    окÑĥ
    -0.15
     oneself
    -0.15
    POSITIVE LOGITS
     themselves
    0.60
     their
    0.29
    Their
    0.28
     Their
    0.28
     leurs
    0.27
    their
    0.24
     they
    0.23
     thems
    0.23
     all
    0.23
     nhau
    0.23
    Activations Density 0.122%

    No Known Activations