© 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. 40897
    Prev
    Next
    INDEX
    Explanations

    references to public opinion and electoral perceptions

    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
    boys
    -0.15
    otics
    -0.15
    æľĭ
    -0.15
     requestOptions
    -0.14
    ëĮĢíĸī
    -0.14
    isman
    -0.14
    ...↵↵↵↵
    -0.14
     boys
    -0.14
    Ĭ¶
    -0.14
    ÅĻiv
    -0.14
    POSITIVE LOGITS
     voters
    0.46
    -v
    0.34
     Voters
    0.33
     elect
    0.32
     voter
    0.32
    Âłv
    0.32
     Elect
    0.30
     vot
    0.30
    v
    0.30
    Elect
    0.28
    Activations Density 0.129%

    No Known Activations