© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 41849
    Prev
    Next
    INDEX
    Explanations

    government, private, local, military entities

    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
     governmental
    -0.22
     governments
    -0.19
     government
    -0.19
     Governments
    -0.15
    government
    -0.15
    -government
    -0.14
    æĶ¿åºľ
    -0.14
     gobierno
    -0.13
     ìłķë¶Ģ
    -0.13
     governo
    -0.13
    POSITIVE LOGITS
     private
    0.25
    private
    0.21
     Private
    0.18
    ç§ģ
    0.17
     PRIVATE
    0.16
    Private
    0.16
    -private
    0.16
    /private
    0.16
    .private
    0.16
    PRIVATE
    0.15
    Activations Density 0.057%

    No Known Activations