© 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. 56576
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by predicate

    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
     weiber
    -0.15
     meisten
    -0.11
     geschichten
    -0.10
     aktuellen
    -0.10
     nächsten
    -0.10
     verschiedenen
    -0.10
     Gilles
    -0.09
     verschied
    -0.09
     titten
    -0.09
    serie
    -0.09
    POSITIVE LOGITS
     die
    0.14
     eine
    0.12
     unk
    0.10
     newer
    0.09
    ver
    0.09
     bei
    0.09
     Revision
    0.09
     sich
    0.09
     massive
    0.09
    еви
    0.08
    Activations Density 0.081%

    No Known Activations