© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35337
    Prev
    Next
    INDEX
    Explanations

    cryptography and computer security

    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
     Bald
    -0.10
    otal
    -0.09
    atetime
    -0.09
    .getFloat
    -0.09
    ìĹ´
    -0.08
    Marks
    -0.08
     capt
    -0.08
     Unary
    -0.08
     bald
    -0.08
     autof
    -0.08
    POSITIVE LOGITS
     Montgomery
    0.16
     Carry
    0.14
     carry
    0.14
    .BigInteger
    0.14
     Big
    0.14
    (BigInteger
    0.13
     div
    0.13
    æº
    0.12
     big
    0.12
     long
    0.12
    Activations Density 0.069%

    No Known Activations