© 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. 45146
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate evaluation or commentary on actions and situations

    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
    aben
    -0.15
    pleasant
    -0.15
    udd
    -0.15
    hlen
    -0.14
    estate
    -0.14
    alon
    -0.14
    елиÑĩ
    -0.13
    lion
    -0.13
    hora
    -0.13
    eyse
    -0.13
    POSITIVE LOGITS
     telling
    0.56
     revealing
    0.51
     tell
    0.46
     instruct
    0.41
     Tell
    0.39
    Tell
    0.38
     tells
    0.38
    tell
    0.38
    reve
    0.37
     illumin
    0.34
    Activations Density 0.028%

    No Known Activations