© 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. 59466
    Prev
    Next
    INDEX
    Explanations

    birthplace and profession

    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
     INST
    -0.09
    ols
    -0.09
     Hum
    -0.09
    cly
    -0.09
     Athena
    -0.09
    plit
    -0.09
    FormField
    -0.09
    ï½ľ
    -0.08
    ardin
    -0.08
     Bast
    -0.08
    POSITIVE LOGITS
     whose
    0.17
     who
    0.14
    active
    0.12
     active
    0.12
    whose
    0.12
     завиÑģим
    0.11
     اÙĩÙĦ
    0.10
    who
    0.10
     ante
    0.10
    embro
    0.10
    Activations Density 0.143%

    No Known Activations