© 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. 9747
    Prev
    Next
    INDEX
    Explanations

    well-defined structure, one blank

    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
    -0.13
     paragraphs
    -0.12
     spells
    -0.11
     pronunciation
    -0.11
     dialect
    -0.11
     Spells
    -0.11
     passages
    -0.11
     Phonetic
    -0.10
     Alphabet
    -0.10
     notation
    -0.10
    POSITIVE LOGITS
     words
    0.16
     subject
    0.16
     Subject
    0.14
    Subject
    0.13
     keywords
    0.13
    Words
    0.13
     subjects
    0.13
    宾
    0.13
     Words
    0.13
     word
    0.12
    Activations Density 0.374%

    No Known Activations