© 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. 8800
    Prev
    Next
    INDEX
    Explanations

    locations or mentions of "here" in relation to discussions about communities and governance

    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
    rol
    -0.16
    ucz
    -0.16
     CGRectGet
    -0.15
     thereof
    -0.14
    aging
    -0.14
    uz
    -0.14
    iete
    -0.14
    rine
    -0.14
    coon
    -0.14
    üss
    -0.14
    POSITIVE LOGITS
    after
    0.19
    ina
    0.18
     locally
    0.17
    ìłĢ
    0.15
    InThe
    0.15
     at
    0.15
    _locals
    0.14
    xdc
    0.14
     onCancelled
    0.14
    à¹ĥà¸Ļ
    0.14
    Activations Density 0.039%

    No Known Activations