© 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. 35589
    Prev
    Next
    INDEX
    Explanations

    grammatical correctness and articles

    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
     spelling
    -0.11
     åŃĹ
    -0.10
    è¯Ń
    -0.09
     nouns
    -0.09
     clave
    -0.09
     subparagraph
    -0.09
    yi
    -0.09
     utter
    -0.09
    208
    -0.08
     sentences
    -0.08
    POSITIVE LOGITS
     articles
    0.16
     apost
    0.15
     Articles
    0.15
     conjunction
    0.15
     article
    0.14
     possess
    0.14
     definite
    0.14
    åĨł
    0.14
     determin
    0.13
    articles
    0.13
    Activations Density 0.150%

    No Known Activations