© 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. 42282
    Prev
    Next
    INDEX
    Explanations

    grammatical and word categories

    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
     gramm
    -0.16
    åŃĹ
    -0.14
     Phonetic
    -0.13
     Vocabulary
    -0.13
     Dictionary
    -0.13
     vocab
    -0.13
    .scalablytyped
    -0.13
     vowels
    -0.12
     åŃĹ
    -0.12
     Grammar
    -0.11
    POSITIVE LOGITS
     interrog
    0.17
     compound
    0.14
     Passive
    0.14
     passive
    0.14
     excl
    0.13
     neg
    0.13
     modal
    0.12
     ger
    0.12
     Imper
    0.12
    Compound
    0.12
    Activations Density 0.368%

    No Known Activations