© 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. 33715
    Prev
    Next
    INDEX
    Explanations

    political discussion and figures

    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
     populist
    -0.10
     Barbar
    -0.10
     Tories
    -0.10
     Conservatives
    -0.10
    Authority
    -0.10
    /ph
    -0.09
    ociety
    -0.09
     Society
    -0.09
     Tory
    -0.09
     drum
    -0.09
    POSITIVE LOGITS
     political
    0.28
     Political
    0.23
    æĶ¿æ²»
    0.19
    political
    0.19
     полиÑĤ
    0.18
    Political
    0.18
     politics
    0.16
     polÃŃtica
    0.15
     party
    0.14
     POL
    0.13
    Activations Density 0.130%

    No Known Activations