© 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. 19249
    Prev
    Next
    INDEX
    Explanations

    two hydroxyl groups

    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
     Diaz
    -0.11
     pap
    -0.10
     Acid
    -0.10
     Salt
    -0.10
    'gc
    -0.10
     coke
    -0.10
    wing
    -0.10
     gas
    -0.10
    apor
    -0.09
     arg
    -0.09
    POSITIVE LOGITS
     alcohol
    0.24
     OH
    0.22
    éħĴ
    0.20
     Alcohol
    0.18
    OH
    0.18
    cohol
    0.17
    anol
    0.17
     rượu
    0.16
    coh
    0.14
    éĨ
    0.14
    Activations Density 0.114%

    No Known Activations