© 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. 51626
    Prev
    Next
    INDEX
    Explanations

    two words maximum

    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
     abbrev
    -0.13
     Alphabet
    -0.13
     pronunciation
    -0.12
     abbreviation
    -0.11
    phabet
    -0.10
    ionales
    -0.10
     acronym
    -0.10
     prefixes
    -0.09
     addCriterion
    -0.09
    quier
    -0.09
    POSITIVE LOGITS
     word
    0.20
    word
    0.18
    -word
    0.16
    Word
    0.16
    _word
    0.16
     Word
    0.15
     WORD
    0.15
    WORD
    0.14
    åįķ
    0.13
    .word
    0.13
    Activations Density 0.160%

    No Known Activations