© 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. 33778
    Prev
    Next
    INDEX
    Explanations

    police officer contexts

    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
     generals
    -0.11
     prosecute
    -0.11
     prosecuting
    -0.11
     prosecutions
    -0.10
     prosecuted
    -0.10
    TEE
    -0.10
    RYPT
    -0.09
    çŃ
    -0.09
     Prosec
    -0.09
     Secretary
    -0.09
    POSITIVE LOGITS
     police
    0.33
     law
    0.28
     Police
    0.26
     officer
    0.25
     badge
    0.25
     uniform
    0.25
     officers
    0.24
    Police
    0.24
    èŃ¦å¯Ł
    0.23
    pol
    0.22
    Activations Density 0.105%

    No Known Activations