© 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. 34819
    Prev
    Next
    INDEX
    Explanations

    in the country, society, favor

    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
    oppins
    -0.09
    ĥ
    -0.09
    inki
    -0.08
     Sloan
    -0.08
     imprint
    -0.08
    owo
    -0.08
     jurisdictions
    -0.08
    Łèĥ½
    -0.08
     outside
    -0.08
    PPER
    -0.08
    POSITIVE LOGITS
     society
    0.29
     Society
    0.20
    ociety
    0.18
     favor
    0.16
     wake
    0.14
     favour
    0.14
     ranks
    0.13
     société
    0.13
     sociedad
    0.13
    wake
    0.13
    Activations Density 0.097%

    No Known Activations