© 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. 28592
    Prev
    Next
    INDEX
    Explanations

    may followed by a verb

    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
     probably
    -0.18
     likely
    -0.14
    probably
    -0.13
     Probably
    -0.13
     usually
    -0.12
     probable
    -0.12
    Probably
    -0.12
     maybe
    -0.11
     Likely
    -0.11
    èĤ¯å®ļ
    -0.11
    POSITIVE LOGITS
     depending
    0.19
    depending
    0.17
     some
    0.14
    some
    0.14
     or
    0.13
     initially
    0.12
     simply
    0.12
    /be
    0.12
    ä¸ĢäºĽ
    0.11
     Depending
    0.11
    Activations Density 0.177%

    No Known Activations