© 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. 45283
    Prev
    Next
    INDEX
    Explanations

    numerical temperature values 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
    raig
    -0.10
    oup
    -0.10
    /cs
    -0.09
     Khoa
    -0.09
    rych
    -0.09
    ThemeProvider
    -0.09
    olg
    -0.08
    ecc
    -0.08
    äº
    -0.08
     plano
    -0.08
    POSITIVE LOGITS
     degrees
    0.18
     degree
    0.17
     Cel
    0.14
    度
    0.14
    æĶĿ
    0.14
    æijĦ
    0.13
    æij
    0.13
     æij
    0.13
    ï¾Ł
    0.12
    -de
    0.12
    Activations Density 0.031%

    No Known Activations