© 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. 53272
    Prev
    Next
    INDEX
    Explanations

    are made from materials

    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
     sometimes
    -0.11
     truly
    -0.10
    毫
    -0.09
    elp
    -0.09
     absolutely
    -0.08
     Mag
    -0.08
     Bour
    -0.08
     lan
    -0.08
     scrim
    -0.08
    739
    -0.08
    POSITIVE LOGITS
     generally
    0.20
     Generally
    0.18
     unlikely
    0.16
    unlikely
    0.15
    Generally
    0.14
     designed
    0.13
    ä¸ĢèĪ¬
    0.12
     geral
    0.12
    gener
    0.12
     Designed
    0.11
    Activations Density 0.115%

    No Known Activations