© 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. 37405
    Prev
    Next
    INDEX
    Explanations

    churchfightermountainpoliticalprogrammingfest

    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
    isha
    -0.10
     impost
    -0.09
     Willie
    -0.08
     sist
    -0.08
     Pete
    -0.08
     contag
    -0.08
     entities
    -0.08
    aggi
    -0.08
    AGMA
    -0.08
    tg
    -0.08
    POSITIVE LOGITS
     adlı
    0.20
    ãģ¨ãģĦãģĨ
    0.17
    ìĿ´ëĿ¼ëĬĶ
    0.15
    ëĿ¼ëĬĶ
    0.14
    ामà¤ķ
    0.13
    ãģªãĤĭ
    0.12
    -brand
    0.10
     nev
    0.10
    ngo
    0.10
    ãģĦãģĨ
    0.10
    Activations Density 0.255%

    No Known Activations