© 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. 11536
    Prev
    Next
    INDEX
    Explanations

    providing details or information

    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
    zelf
    -0.13
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.11
    TEGER
    -0.09
    /******/
    -0.08
    /of
    -0.08
    jen
    -0.08
    -même
    -0.08
    åľ³
    -0.08
     addCriterion
    -0.08
    ãĤĪãģ³
    -0.08
    POSITIVE LOGITS
    /-
    0.13
    (sp
    0.12
    theless
    0.11
    ÌĨ
    0.11
    terior
    0.10
    etheless
    0.10
    gether
    0.10
    -vous
    0.09
    âĢĮترÛĮÙĨ
    0.09
    OGLE
    0.09
    Activations Density 0.402%

    No Known Activations