© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 838
    Prev
    Next
    INDEX
    Explanations

    controversial leaders and politicians

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ambassadors
    -0.12
     councils
    -0.11
    ostel
    -0.10
     coquine
    -0.10
     presidency
    -0.10
     Legendary
    -0.09
     Presidency
    -0.09
     Maher
    -0.09
    cona
    -0.09
    олÑĮно
    -0.09
    POSITIVE LOGITS
     politicians
    0.34
     leaders
    0.34
     officials
    0.33
     politician
    0.32
     elected
    0.27
     Leaders
    0.26
     leader
    0.25
     dign
    0.24
     Officials
    0.24
    Officials
    0.23
    Activations Density 0.131%

    No Known Activations