© 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. 24615
    Prev
    Next
    INDEX
    Explanations

    group size or number of people

    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
    olders
    -0.11
    OTH
    -0.11
    mens
    -0.10
    KHTML
    -0.09
     Evel
    -0.09
    __$
    -0.09
    /Grid
    -0.09
     гÑĢаж
    -0.08
    leur
    -0.08
     holders
    -0.08
    POSITIVE LOGITS
    两人
    0.17
     parties
    0.17
     ÙĨÙģر
    0.17
     adults
    0.15
     persons
    0.15
     four
    0.14
     groups
    0.14
    人
    0.14
     party
    0.14
     people
    0.14
    Activations Density 0.186%

    No Known Activations