© 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. 7877
    Prev
    Next
    INDEX
    Explanations

    listing ingredients

    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
    izza
    -0.11
     grated
    -0.10
    _HS
    -0.09
    avis
    -0.09
     meats
    -0.09
    asley
    -0.09
    ",__
    -0.09
     plung
    -0.09
     Soup
    -0.09
     tea
    -0.08
    POSITIVE LOGITS
     deg
    0.19
     Deg
    0.17
     mushrooms
    0.16
    Deg
    0.15
     jus
    0.14
     mushroom
    0.14
     Mars
    0.14
     cogn
    0.14
     reduction
    0.13
     wine
    0.13
    Activations Density 0.029%

    No Known Activations