© 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. 33859
    Prev
    Next
    INDEX
    Explanations

    nor, ni, yet, till, pra conjunctions

    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
    ses
    -0.11
    alus
    -0.10
    /or
    -0.09
    ials
    -0.09
    ially
    -0.09
    nt
    -0.09
    اتÙĩ
    -0.09
    verse
    -0.08
    sse
    -0.08
    s
    -0.08
    POSITIVE LOGITS
    forth
    0.15
    ogh
    0.13
    Å¡tÄĽnÃŃ
    0.13
    že
    0.12
    ï¸ı
    0.12
    /OR
    0.12
    Ú©ÙĨ
    0.12
    ÑĶм
    0.11
    out
    0.10
    gether
    0.10
    Activations Density 0.292%

    No Known Activations