© 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. 59413
    Prev
    Next
    INDEX
    Explanations

    these, them, those, the

    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
     its
    -0.09
    è¿Ļ个
    -0.09
    Its
    -0.09
    å®ĥ
    -0.09
    thew
    -0.09
     оно
    -0.08
    éĤ£ä¸ª
    -0.08
     Its
    -0.08
     ëijĺ
    -0.08
    两人
    -0.08
    POSITIVE LOGITS
     these
    0.49
    è¿ĻäºĽ
    0.39
    these
    0.38
     These
    0.35
    These
    0.33
     THESE
    0.31
     those
    0.30
     ÑįÑĤиÑħ
    0.30
     them
    0.27
     ÑįÑĤи
    0.26
    Activations Density 0.337%

    No Known Activations