© 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. 29994
    Prev
    Next
    INDEX
    Explanations

    words counted or described

    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
     Phonetic
    -0.15
     shorthand
    -0.12
     Alphabet
    -0.12
    ingu
    -0.11
     pronunciation
    -0.11
     acronym
    -0.10
     grammar
    -0.10
    丶
    -0.10
     abbrev
    -0.10
     gramm
    -0.10
    POSITIVE LOGITS
     words
    0.59
     word
    0.52
    words
    0.43
     Words
    0.43
    word
    0.39
    Words
    0.38
     Ñģлова
    0.36
    _words
    0.35
     palabras
    0.35
    -word
    0.34
    Activations Density 0.331%

    No Known Activations