© 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. 30293
    Prev
    Next
    INDEX
    Explanations

    phrases related to representation and political interests

    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
    uchi
    -0.17
    ServiceProvider
    -0.14
    ¶Į
    -0.14
    apter
    -0.14
    PTS
    -0.14
    etto
    -0.14
    ngr
    -0.14
    仲
    -0.14
    bolt
    -0.14
    edu
    -0.14
    POSITIVE LOGITS
     interests
    1.12
     interest
    0.83
    interest
    0.81
     Interest
    0.69
    -interest
    0.69
     interes
    0.64
    Interest
    0.64
     инÑĤеÑĢеÑģ
    0.63
    _interest
    0.62
     interess
    0.58
    Activations Density 0.047%

    No Known Activations