© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 16633
    Prev
    Next
    INDEX
    Explanations

    energy, power, data

    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
    身ä¸Ĭ
    -0.11
    775
    -0.09
    eam
    -0.08
    ä¹ĭä¸Ģ
    -0.08
    ī
    -0.08
     sweaty
    -0.08
    916
    -0.08
    atal
    -0.08
     intact
    -0.08
    uit
    -0.08
    POSITIVE LOGITS
     lax
    0.09
    tober
    0.09
     Hv
    0.09
    daq
    0.09
    anyak
    0.09
    AGER
    0.08
    ä¼ĺåĬ¿
    0.08
    aja
    0.08
     equal
    0.08
     dollars
    0.08
    Activations Density 0.125%

    No Known Activations