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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 52443
    Prev
    Next
    INDEX
    Explanations

    political systems and governance

    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
    æĶ¿æ²»
    -0.14
     political
    -0.12
     politics
    -0.11
    political
    -0.10
     conj
    -0.10
     amateur
    -0.10
     Politics
    -0.10
    Politics
    -0.10
     POLIT
    -0.10
     ÙĪرز
    -0.09
    POSITIVE LOGITS
     merit
    0.16
     bene
    0.14
     olig
    0.13
    Merit
    0.12
     monarchy
    0.11
    egal
    0.11
     techn
    0.11
     plut
    0.11
     aut
    0.10
    ocracy
    0.10
    Activations Density 0.111%

    No Known Activations