© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 38997
    Prev
    Next
    INDEX
    Explanations

    detecting and deleting outliers

    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
    .:.
    -0.09
     bö
    -0.09
     openings
    -0.09
    trak
    -0.09
     Yaz
    -0.09
    edReader
    -0.09
    EP
    -0.08
    ptr
    -0.08
     Shak
    -0.08
     decre
    -0.08
    POSITIVE LOGITS
     extreme
    0.27
     Out
    0.23
     Extreme
    0.22
     outliers
    0.22
     outlier
    0.22
    Extreme
    0.21
    liers
    0.19
    Out
    0.18
    _out
    0.17
     dev
    0.16
    Activations Density 0.051%

    No Known Activations