© 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. 53372
    Prev
    Next
    INDEX
    Explanations

    audience MPS Network casting

    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
    ฯ
    -0.09
     baģlantılar
    -0.09
    bai
    -0.08
    azÄĥ
    -0.08
    \tROM
    -0.08
    ITHER
    -0.07
     Sext
    -0.07
    etooth
    -0.07
     ëķĮ문
    -0.07
    ÑĤÑĮ
    -0.07
    POSITIVE LOGITS
    orch
    0.09
    (Syntax
    0.08
    ¡
    0.08
    âĢį
    0.07
     hoặc
    0.07
    'S
    0.07
    âĢ°
    0.07
     +
    0.07
     Prem
    0.07
    ãĤ
    0.07
    Activations Density 0.116%

    No Known Activations