© 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. 53551
    Prev
    Next
    INDEX
    Explanations

    past impact and improvements

    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
    .Dto
    -0.10
     поба
    -0.09
    prak
    -0.09
    achi
    -0.09
    hci
    -0.08
    ä½µ
    -0.08
     assistir
    -0.08
    _MEM
    -0.08
    atk
    -0.08
    jišť
    -0.08
    POSITIVE LOGITS
    æıIJé«ĺ
    0.13
     improve
    0.12
     improved
    0.12
     improvement
    0.12
     potentially
    0.11
     resulting
    0.11
     provide
    0.10
     improves
    0.10
     improvements
    0.10
     increase
    0.10
    Activations Density 0.112%

    No Known Activations