© 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. 25724
    Prev
    Next
    INDEX
    Explanations

    United Nations population data

    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
     pregnant
    -0.09
     paternal
    -0.09
     Civ
    -0.09
     Pregnancy
    -0.09
     unp
    -0.08
    _PADDING
    -0.08
     Pregn
    -0.08
    ale
    -0.08
     routing
    -0.08
    èĭ
    -0.08
    POSITIVE LOGITS
     population
    0.30
     Population
    0.26
    Population
    0.24
    population
    0.24
     demographic
    0.21
     dem
    0.20
    人åı£
    0.18
    .population
    0.18
     ìĿ¸êµ¬
    0.17
     Dem
    0.16
    Activations Density 0.047%

    No Known Activations