© 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. 29786
    Prev
    Next
    INDEX
    Explanations

    references to political figures and controversies

    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
     Against
    -0.32
     against
    -0.29
    against
    -0.29
    Against
    -0.29
     пÑĢоÑĤи
    -0.25
    contre
    -0.23
     gegen
    -0.22
     contre
    -0.21
     proti
    -0.21
     tegen
    -0.21
    POSITIVE LOGITS
     perceived
    0.26
     over
    0.25
     for
    0.21
     behalf
    0.18
     specifically
    0.17
    åıĬåħ¶
    0.16
    overe
    0.16
     tooth
    0.16
     MainAxisAlignment
    0.15
    over
    0.15
    Activations Density 0.159%

    No Known Activations