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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 43827
    Prev
    Next
    INDEX
    Explanations

    adjectives and comparative terms related to effectiveness and health

    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
     enough
    -0.24
    son
    -0.22
     Enough
    -0.19
    so
    -0.18
    vers
    -0.17
    site
    -0.17
    ses
    -0.17
    sj
    -0.17
    itude
    -0.16
    enh
    -0.15
    POSITIVE LOGITS
    -than
    0.75
     than
    0.58
    than
    0.56
    _than
    0.49
     THAN
    0.46
    Than
    0.44
     Than
    0.43
     niż
    0.36
    _THAN
    0.33
     než
    0.33
    Activations Density 0.300%

    No Known Activations