© 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. 31386
    Prev
    Next
    INDEX
    Explanations

    quantifiers and "other"

    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
     stuff
    -0.14
     things
    -0.12
     thing
    -0.12
    ä¸ľè¥¿
    -0.10
     material
    -0.10
     items
    -0.09
     topics
    -0.09
    things
    -0.09
     components
    -0.08
     Inherits
    -0.08
    POSITIVE LOGITS
     other
    0.11
     autres
    0.11
    agogue
    0.10
    ãģ£ãģ¨
    0.08
     otras
    0.08
     anderen
    0.08
    gin
    0.08
     existing
    0.08
    inger
    0.08
     hallmark
    0.08
    Activations Density 0.218%

    No Known Activations