© 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. 45081
    Prev
    Next
    INDEX
    Explanations

    openpyxl, Open Assistant/Radio/Wrt

    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
     openings
    -0.10
    olet
    -0.10
    iddy
    -0.09
     Peek
    -0.09
     Mey
    -0.09
    oops
    -0.09
    èĪĪ
    -0.09
    448
    -0.09
     ï¿¥
    -0.09
     Hose
    -0.08
    POSITIVE LOGITS
     Open
    0.19
    .Open
    0.16
     setOpen
    0.16
     Closed
    0.16
    Open
    0.16
    /Open
    0.15
    /open
    0.14
    (open
    0.14
    Closed
    0.14
    (O
    0.13
    Activations Density 0.071%

    No Known Activations