© 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. 10249
    Prev
    Next
    INDEX
    Explanations

    Polish verbs for state or completion

    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
    íģ¬ê¸°
    -0.10
    ãģĵãģ¨ãģ§
    -0.10
    -toggler
    -0.09
    ê¸°ë¡ľ
    -0.09
     -*-č\n
    -0.09
    низ
    -0.09
    jsc
    -0.09
    -has
    -0.09
    \tROM
    -0.09
    (is
    -0.08
    POSITIVE LOGITS
     are
    0.13
     zosta
    0.13
     zost
    0.12
     cannot
    0.12
     بÛĮشترÛĮ
    0.11
     was
    0.11
     is
    0.11
     were
    0.11
    *
    0.11
     could
    0.11
    Activations Density 0.418%

    No Known Activations