© 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. 42554
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of different subjects, possibly pertaining to political figures or events

    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
    Ł
    -0.17
     Bry
    -0.14
    quet
    -0.14
    ëĮĢíķĻêµIJ
    -0.14
     licking
    -0.13
    ÙĪÙģ
    -0.13
     Bias
    -0.13
    ÏĦÏģ
    -0.13
     Kil
    -0.13
     fades
    -0.13
    POSITIVE LOGITS
    30
    0.89
     Thirty
    0.63
     thirty
    0.61
    Thirty
    0.55
    Û³Û°
    0.55
    030
    0.49
    31
    0.41
    330
    0.35
    29
    0.33
    930
    0.31
    Activations Density 0.009%

    No Known Activations