© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38336
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by potential actions

    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
    Negative Logits
    ANDLE
    -0.09
    uits
    -0.09
    olo
    -0.09
    otic
    -0.09
    ERENCE
    -0.09
    innie
    -0.09
    yles
    -0.08
     Nicholson
    -0.08
    uada
    -0.08
    anned
    -0.08
    POSITIVE LOGITS
     might
    0.19
     will
    0.18
     likely
    0.17
     sẽ
    0.15
    might
    0.14
    ä¸Ģå®ļ
    0.14
     appreciate
    0.14
     would
    0.14
     enjoy
    0.14
     enjoyed
    0.13
    Activations Density 0.077%

    No Known Activations