© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35550
    Prev
    Next
    INDEX
    Explanations

    should and will

    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
     kön
    -0.10
     dür
    -0.10
     Might
    -0.10
    asso
    -0.09
     мÑĸг
    -0.09
    arov
    -0.09
    erland
    -0.09
     Could
    -0.09
    881
    -0.08
     Pear
    -0.08
    POSITIVE LOGITS
     should
    0.40
     shall
    0.35
    should
    0.31
    åºĶ该
    0.29
     sollen
    0.29
    Should
    0.29
     Should
    0.29
    shall
    0.28
     soll
    0.27
     sollte
    0.26
    Activations Density 0.191%

    No Known Activations