© 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. 27764
    Prev
    Next
    INDEX
    Explanations

    mathematical explanations starting with "The"

    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
    adin
    -0.10
    .IsSuccess
    -0.09
    most
    -0.09
    _MetaData
    -0.09
    #
    -0.09
     possibility
    -0.09
    lescope
    -0.09
    _rl
    -0.08
    .restart
    -0.08
    GenerationStrategy
    -0.08
    POSITIVE LOGITS
     trick
    0.17
    orem
    0.15
     formula
    0.15
     steps
    0.15
     Trick
    0.13
     Steps
    0.12
     correct
    0.11
     easiest
    0.10
     equation
    0.10
     reason
    0.10
    Activations Density 0.090%

    No Known Activations