© 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. 38915
    Prev
    Next
    INDEX
    Explanations

    her way

    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
     drowning
    -0.11
     Tong
    -0.09
    ãĥĪãĥª
    -0.09
     mastur
    -0.09
     sclerosis
    -0.09
     cÆ°á»Ŀi
    -0.09
    ASTER
    -0.09
     Sachs
    -0.09
    usercontent
    -0.08
     tong
    -0.08
    POSITIVE LOGITS
     rag
    0.11
     improvis
    0.11
     ration
    0.11
     jag
    0.11
     survival
    0.10
     lim
    0.10
     irregular
    0.10
     Orient
    0.10
    collapsed
    0.10
     Alley
    0.10
    Activations Density 0.052%

    No Known Activations