© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25999
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or negative outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     indeed
    -0.25
     however
    -0.20
     nevertheless
    -0.19
     nonetheless
    -0.19
     certainly
    -0.19
    thus
    -0.18
     thus
    -0.18
     meanwhile
    -0.18
     obviously
    -0.18
     therefore
    -0.17
    POSITIVE LOGITS
     even
    0.30
     probably
    0.29
    even
    0.28
    probably
    0.28
     quite
    0.27
     downright
    0.27
     sogar
    0.26
     precisely
    0.24
     exactly
    0.22
    quite
    0.22
    Activations Density 0.062%

    No Known Activations