© 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. 11306
    Prev
    Next
    INDEX
    Explanations

    a/an before chemical descriptors

    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
     Norse
    -0.11
    ç¡
    -0.10
     Si
    -0.10
     Magnum
    -0.09
     alk
    -0.09
    å±ĭ
    -0.09
     Snyder
    -0.09
     bands
    -0.09
     заÑģÑĤ
    -0.09
    ssi
    -0.09
    POSITIVE LOGITS
     acid
    0.20
     Acid
    0.17
     acids
    0.17
     tart
    0.16
    acid
    0.15
    éħ¸
    0.14
     Tart
    0.14
     sour
    0.14
     car
    0.13
     dik
    0.13
    Activations Density 0.172%

    No Known Activations