© 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. 42806
    Prev
    Next
    INDEX
    Explanations

    references to political incompetence and corruption

    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
     mostly
    -0.15
     till
    -0.14
    zá
    -0.14
     usually
    -0.13
     eldre
    -0.13
     soon
    -0.13
     yearly
    -0.13
     Soon
    -0.13
    zan
    -0.13
    åIJįçĦ¡ãģĹãģķãĤĵ
    -0.13
    POSITIVE LOGITS
     absolutely
    0.19
    amedi
    0.16
     whenever
    0.15
    adin
    0.15
    ën
    0.15
    Whenever
    0.15
     --
    0.15
    èĥ½å¤Ł
    0.14
    uel
    0.14
     exactly
    0.14
    Activations Density 0.561%

    No Known Activations