© 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. 45155
    Prev
    Next
    INDEX
    Explanations

    #include *

    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
    895
    -0.10
    ``\n
    -0.10
    arty
    -0.09
     Fol
    -0.09
     Chapman
    -0.08
     Gir
    -0.08
    odos
    -0.08
     Milo
    -0.08
     indifference
    -0.08
     Thur
    -0.08
    POSITIVE LOGITS
    Č\n
    0.12
    agus
    0.10
    íĨłíĨł
    0.10
    cape
    0.10
    kel
    0.09
     Hussein
    0.09
    /../
    0.09
    beb
    0.09
    -lnd
    0.09
     (*((
    0.09
    Activations Density 0.122%

    No Known Activations