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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41865
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize similarity or comparison

    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
     âĨIJ
    -0.16
     Larger
    -0.16
    orne
    -0.15
    aida
    -0.15
    iaux
    -0.15
    ronics
    -0.14
    bett
    -0.14
    ozo
    -0.14
    تÙĪ
    -0.14
     edilmesi
    -0.14
    POSITIVE LOGITS
     old
    1.04
     ol
    0.95
    -old
    0.86
    old
    0.83
     ole
    0.78
    (old
    0.68
     OLD
    0.67
    .old
    0.65
    _old
    0.61
     olds
    0.60
    Activations Density 0.021%

    No Known Activations