© 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. 39286
    Prev
    Next
    INDEX
    Explanations

    quantities and units

    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
     {}:
    -0.13
     nÄĽkolika
    -0.10
     birkaç
    -0.09
    åĩł
    -0.09
    abbr
    -0.09
     vÃłi
    -0.09
    ono
    -0.09
    åįģä¸Ģ
    -0.09
    veral
    -0.09
    onces
    -0.09
    POSITIVE LOGITS
     exactly
    0.15
     approximately
    0.14
     whopping
    0.14
     dalÅ¡ÃŃch
    0.11
     Exactly
    0.10
     ì´Ŀ
    0.10
     cov
    0.10
    ellow
    0.09
    Exactly
    0.09
     celkem
    0.09
    Activations Density 0.226%

    No Known Activations