© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 5670
    Prev
    Next
    INDEX
    Explanations

    agan por ellos

    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
    Negative Logits
    licer
    -0.10
    oops
    -0.10
    .biz
    -0.09
     dept
    -0.09
     nto
    -0.09
    usal
    -0.09
     Estr
    -0.09
    ï¼ģãĢį\n\n
    -0.08
    Cli
    -0.08
    ÇIJ
    -0.08
    POSITIVE LOGITS
     follando
    0.10
     lo
    0.10
     Lo
    0.09
     enam
    0.09
     mach
    0.09
     apart
    0.09
     inp
    0.09
    arme
    0.09
     inclusive
    0.09
     rab
    0.09
    Activations Density 0.104%

    No Known Activations