© 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. 22901
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reluctance or avoidance in discussions

    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
     Dop
    -0.16
     Ding
    -0.16
     dop
    -0.15
     Demp
    -0.15
    ida
    -0.15
    IDA
    -0.15
    [dim
    -0.14
    displayName
    -0.14
    dra
    -0.14
     Damascus
    -0.14
    POSITIVE LOGITS
     DET
    0.49
     details
    0.46
     det
    0.45
     detail
    0.43
    Det
    0.42
     Det
    0.41
    -details
    0.39
    -det
    0.39
    details
    0.38
    det
    0.38
    Activations Density 0.049%

    No Known Activations