© 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. 30622
    Prev
    Next
    INDEX
    Explanations

    minimum system requirements

    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
    umer
    -0.12
    'gc
    -0.10
     dereg
    -0.09
     Rate
    -0.09
     limited
    -0.09
     rate
    -0.09
    lasting
    -0.09
    anik
    -0.09
     reprint
    -0.09
     Maxim
    -0.08
    POSITIVE LOGITS
     minimum
    0.29
     Minimum
    0.25
    minimum
    0.23
    Minimum
    0.22
     mÃŃnimo
    0.17
     running
    0.17
     requirements
    0.17
    _minimum
    0.16
     ØŃداÙĤÙĦ
    0.14
    .minimum
    0.14
    Activations Density 0.087%

    No Known Activations