© 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. 38940
    Prev
    Next
    INDEX
    Explanations

    family structures

    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
     Pregn
    -0.10
    å¦ĥ
    -0.09
     Cous
    -0.09
    .friends
    -0.09
    Girls
    -0.09
     Cousins
    -0.09
     Girls
    -0.09
     friendship
    -0.08
     PureComponent
    -0.08
    abeth
    -0.08
    POSITIVE LOGITS
     family
    0.44
    family
    0.34
     Family
    0.32
    Family
    0.30
     FAMILY
    0.29
    家åºŃ
    0.29
    -family
    0.28
    .family
    0.27
    家æĹı
    0.27
     Ñģемей
    0.27
    Activations Density 0.325%

    No Known Activations