© 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. 44813
    Prev
    Next
    INDEX
    Explanations

    phrases expressing evaluation or recommendation

    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
    ontent
    -0.15
    ULLET
    -0.14
     lis
    -0.14
    à¸Ĭาà¸ķ
    -0.14
     femin
    -0.13
    èī
    -0.13
    ivatel
    -0.13
    enor
    -0.13
    ela
    -0.13
    _tl
    -0.13
    POSITIVE LOGITS
     useful
    0.69
     Useful
    0.60
     helpful
    0.56
     полез
    0.48
     Helpful
    0.47
     usefulness
    0.46
     handy
    0.46
     valuable
    0.40
     Handy
    0.38
     hữu
    0.35
    Activations Density 0.075%

    No Known Activations