© 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. 45049
    Prev
    Next
    INDEX
    Explanations

    organic chemical names and reactions

    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
    ogan
    -0.12
    sh
    -0.12
    ress
    -0.11
    down
    -0.11
    te
    -0.11
    room
    -0.11
    den
    -0.11
    ton
    -0.11
    rec
    -0.11
    rom
    -0.10
    POSITIVE LOGITS
     oxide
    0.15
     gly
    0.13
    burg
    0.13
    oxide
    0.13
    bis
    0.11
    vÃŃ
    0.10
     Gly
    0.10
    é¨
    0.10
    based
    0.09
    -prop
    0.09
    Activations Density 0.052%

    No Known Activations