© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 21767
    Prev
    Next
    INDEX
    Explanations

    corrupted russian punctuation

    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
    agu
    -0.10
     Fountain
    -0.09
    yum
    -0.09
     vib
    -0.08
     chilled
    -0.08
    ãĢĢãĤĿ
    -0.08
    ynes
    -0.08
     Compression
    -0.08
    844
    -0.08
    ignet
    -0.08
    POSITIVE LOGITS
     ventilation
    0.38
     Vent
    0.38
    vent
    0.36
     ventil
    0.32
     vent
    0.31
     венÑĤи
    0.31
    Vent
    0.31
     air
    0.29
    vents
    0.23
    VENT
    0.23
    Activations Density 0.034%

    No Known Activations