© 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. 5636
    Prev
    Next
    INDEX
    Explanations

    objects and classes

    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
    趣
    -0.09
    à¸ķร
    -0.09
    ازد
    -0.09
    fec
    -0.09
    PostalCodes
    -0.09
    ajar
    -0.08
    ¶Į
    -0.08
    onet
    -0.08
     subtree
    -0.08
     subsets
    -0.08
    POSITIVE LOGITS
     classes
    0.20
     objects
    0.17
     class
    0.16
     variables
    0.15
     object
    0.14
     Classes
    0.13
    classes
    0.13
    对象
    0.12
    Classes
    0.12
     tables
    0.12
    Activations Density 0.293%

    No Known Activations