© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 30206
    Prev
    Next
    INDEX
    Explanations

    references to right-wing political figures and ideologies

    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
    ((-
    -0.15
    باÙĨ
    -0.14
    atter
    -0.14
    ilde
    -0.14
    ÑĥÑĢн
    -0.14
    iners
    -0.14
     +=↵
    -0.14
    eur
    -0.14
    ÙĪج
    -0.14
    etus
    -0.13
    POSITIVE LOGITS
    -leaning
    0.21
    /lib
    0.18
     radio
    0.18
     leaning
    0.18
     websites
    0.17
    -friendly
    0.17
     groups
    0.17
     website
    0.17
     publications
    0.17
     think
    0.16
    Activations Density 0.057%

    No Known Activations