© 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. 44239
    Prev
    Next
    INDEX
    Explanations

    moody old fart

    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
    EMPLARY
    -0.13
    ÂĢÂĢ
    -0.11
     nackt
    -0.09
     kariy
    -0.09
    ETO
    -0.09
     tack
    -0.09
    vÄĽd
    -0.09
    ë¦
    -0.09
     patter
    -0.09
    /ï¼ı
    -0.09
    POSITIVE LOGITS
     gr
    0.16
     old
    0.14
     Mood
    0.13
    old
    0.13
    -old
    0.12
     mood
    0.12
    Old
    0.12
     OLD
    0.12
    ing
    0.12
     Old
    0.11
    Activations Density 0.056%

    No Known Activations