© 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. 57400
    Prev
    Next
    INDEX
    Explanations

    multilingual pronouns such as 'they'

    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
    ´Ī
    -0.10
    âĢ¦the
    -0.10
    ITAL
    -0.10
     the
    -0.10
    ITT
    -0.09
     ÙħÙĨÙĩ
    -0.08
     Ital
    -0.08
    该
    -0.08
     The
    -0.08
    (iterator
    -0.08
    POSITIVE LOGITS
     it
    0.35
    å®ĥ
    0.34
     they
    0.28
     оно
    0.27
     nó
    0.27
    ï¼Įå®ĥ
    0.23
    they
    0.23
     они
    0.22
    They
    0.20
     воно
    0.20
    Activations Density 0.345%

    No Known Activations