© 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. 39280
    Prev
    Next
    INDEX
    Explanations

    minimum minimal

    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
     remainder
    -0.11
     Sans
    -0.11
     diminishing
    -0.10
     simpl
    -0.10
     insufficient
    -0.09
     stream
    -0.09
    XMLLoader
    -0.09
     completely
    -0.09
     mej
    -0.09
     Horton
    -0.09
    POSITIVE LOGITS
     minimum
    0.51
     minimal
    0.44
    minimum
    0.41
     Minimum
    0.40
    Minimum
    0.38
     mÃŃnimo
    0.36
    minimal
    0.35
     миним
    0.35
    Minimal
    0.34
     Minimal
    0.33
    Activations Density 0.136%

    No Known Activations