© 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. 10772
    Prev
    Next
    INDEX
    Explanations

    chemical reactions

    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
     chemicals
    -0.12
     chemistry
    -0.12
     Chemistry
    -0.11
    evil
    -0.09
    chemistry
    -0.09
    ams
    -0.09
    achs
    -0.09
    ãĤ¡
    -0.08
     Minerals
    -0.08
    orch
    -0.08
    POSITIVE LOGITS
     reactions
    0.18
     reaction
    0.17
    åıįåºĶ
    0.13
     Reaction
    0.12
    Reaction
    0.12
    /math
    0.11
    reaction
    0.11
     warfare
    0.11
    /material
    0.11
     ÑĢеак
    0.11
    Activations Density 0.025%

    No Known Activations