© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 9974
    Prev
    Next
    INDEX
    Explanations

    YAML Ain't Markup Language

    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
    Not in Any Lists

    No Comments

    Negative Logits
     unstable
    -0.10
     scri
    -0.09
     hod
    -0.09
     Bates
    -0.09
     Verified
    -0.09
    ilter
    -0.09
     Suff
    -0.09
     пÑĢиг
    -0.09
     Sap
    -0.09
     zip
    -0.09
    POSITIVE LOGITS
    Y
    0.20
    yaml
    0.18
     YAML
    0.18
     Y
    0.17
    .yaml
    0.17
     yaml
    0.17
    .Y
    0.15
    .yml
    0.14
    =Y
    0.14
    \tY
    0.13
    Activations Density 0.042%

    No Known Activations