© 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. 45060
    Prev
    Next
    INDEX
    Explanations

    inappropriate, hast, nutrition, code, expected, pork

    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
     however
    -0.14
    indow
    -0.12
    MBER
    -0.10
     nonetheless
    -0.10
     despite
    -0.10
    oma
    -0.10
     trotz
    -0.09
     æĻ´
    -0.09
    aled
    -0.09
    Anywhere
    -0.09
    POSITIVE LOGITS
     anyway
    0.56
    Anyway
    0.54
     Anyway
    0.47
     anyways
    0.30
     zaten
    0.22
     stejnÄĽ
    0.20
     ÑĢавно
    0.17
     toch
    0.17
     jeden
    0.15
    åĺĽ
    0.14
    Activations Density 0.105%

    No Known Activations