© 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. 44236
    Prev
    Next
    INDEX
    Explanations

    age and gender descriptions

    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
     aged
    -0.15
     Ages
    -0.10
     Older
    -0.10
     elderly
    -0.10
    ĥĿ
    -0.10
    588
    -0.09
     underage
    -0.09
     yaÅŁlı
    -0.09
    wner
    -0.09
     teenage
    -0.09
    POSITIVE LOGITS
    -old
    0.15
     males
    0.15
     male
    0.14
     woman
    0.13
    -fashioned
    0.12
    -olds
    0.11
     boy
    0.11
     girl
    0.11
     female
    0.10
     Male
    0.10
    Activations Density 0.055%

    No Known Activations