© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 5383
    Prev
    Next
    INDEX
    Explanations

    rules and grammar

    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
     Vocabulary
    -0.17
     vocab
    -0.16
     vocabulary
    -0.14
     Phonetic
    -0.13
     spelling
    -0.13
     synonyms
    -0.13
     Gloss
    -0.12
    vocab
    -0.12
    åŃĹ
    -0.12
     vowels
    -0.11
    POSITIVE LOGITS
     rules
    0.24
     Rules
    0.21
    rules
    0.19
     rule
    0.19
    Rules
    0.17
     RULE
    0.17
     gram
    0.17
    è§Ħ
    0.17
     Rule
    0.16
    _rules
    0.16
    Activations Density 0.219%

    No Known Activations