© 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. 18003
    Prev
    Next
    INDEX
    Explanations

    that + possibility/existence

    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
    ãģĤãĤĭ
    -0.11
    877
    -0.10
    uppe
    -0.09
    rlen
    -0.09
     piger
    -0.09
    771
    -0.09
    706
    -0.09
    rosso
    -0.08
    956
    -0.08
    ãģ«ãģ¯
    -0.08
    POSITIVE LOGITS
     might
    0.43
     may
    0.36
    might
    0.30
    may
    0.25
     Might
    0.24
    à¸Ńาà¸Ī
    0.23
     maybe
    0.23
    åı¯èĥ½
    0.23
     może
    0.21
     могÑĥÑĤ
    0.21
    Activations Density 0.045%

    No Known Activations