© 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 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. 14726
    Prev
    Next
    INDEX
    Explanations

    numerical representations and statistical measures regarding ideology

    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
     prob
    -0.17
    ools
    -0.14
    din
    -0.13
    äter
    -0.13
    buzz
    -0.13
    _FORCE
    -0.13
    pch
    -0.12
    ware
    -0.12
    знаÑĩа
    -0.12
     Leon
    -0.12
    POSITIVE LOGITS
     minus
    0.50
     negative
    0.49
     (-
    0.46
     `-
    0.45
     Negative
    0.42
    (-
    0.41
    {-
    0.39
     [-
    0.39
    negative
    0.38
    =-
    0.38
    Activations Density 0.064%

    No Known Activations