© 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. 22334
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical data and voting

    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
     from
    -0.31
    ä»İ
    -0.27
    from
    -0.27
    å¾ŀ
    -0.26
     från
    -0.24
     từ
    -0.23
     FROM
    -0.22
    FromString
    -0.21
    FromFile
    -0.21
     dari
    -0.21
    POSITIVE LOGITS
     standpoint
    0.45
     perspective
    0.41
     Perspective
    0.33
     perspectives
    0.32
     sources
    0.31
     viewpoint
    0.26
     onwards
    0.25
    sources
    0.25
     Sources
    0.25
     source
    0.25
    Activations Density 0.074%

    No Known Activations