© 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. 62899
    Prev
    Next
    INDEX
    Explanations

    many followed by a noun and 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
     generally
    -0.10
     sometimes
    -0.10
    们
    -0.10
    ä¸ĢåĪĩ
    -0.10
     mostly
    -0.09
     Braun
    -0.09
    aybe
    -0.09
    ffield
    -0.09
    _ALWAYS
    -0.09
     може
    -0.09
    POSITIVE LOGITS
     either
    0.13
     today
    0.13
     simply
    0.12
    -many
    0.12
     including
    0.11
     vÄįetnÄĽ
    0.11
     Including
    0.11
    hare
    0.11
     across
    0.11
     worldwide
    0.10
    Activations Density 0.116%

    No Known Activations