© 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. 39563
    Prev
    Next
    INDEX
    Explanations

    police and investigation

    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
    udit
    -0.10
     firefight
    -0.10
    .myapplication
    -0.10
     firefighter
    -0.09
    ritch
    -0.09
    umo
    -0.09
    åĽ
    -0.08
    588
    -0.08
    efa
    -0.08
     Libre
    -0.08
    POSITIVE LOGITS
     authorities
    0.44
     police
    0.38
     Authorities
    0.29
     Police
    0.26
    èŃ¦å¯Ł
    0.26
    Authorities
    0.25
     law
    0.23
    Police
    0.23
     поли
    0.22
     полÑĸ
    0.22
    Activations Density 0.073%

    No Known Activations