© 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. 64138
    Prev
    Next
    INDEX
    Explanations

    sure 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
     perhaps
    -0.15
     maybe
    -0.13
    ä¼¼ä¹İ
    -0.12
     sanki
    -0.11
    à¸Ńาà¸Ī
    -0.11
    might
    -0.10
     seems
    -0.10
     possibly
    -0.10
    agn
    -0.10
     Perhaps
    -0.10
    POSITIVE LOGITS
     plenty
    0.16
     will
    0.11
     probably
    0.11
    ustin
    0.11
     Plenty
    0.10
     somewhere
    0.10
     Probably
    0.10
     would
    0.10
    Probably
    0.10
     wouldn
    0.09
    Activations Density 0.057%

    No Known Activations