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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37616
    Prev
    Next
    INDEX
    Explanations

    writes per transaction

    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
     Michigan
    -0.17
     Detroit
    -0.15
    _mysql
    -0.14
    Michigan
    -0.13
     MySQL
    -0.13
    MySQL
    -0.12
     MYSQL
    -0.11
    Detroit
    -0.11
    mysql
    -0.11
     mysql
    -0.11
    POSITIVE LOGITS
     Post
    0.22
    Post
    0.20
     PG
    0.17
    .Post
    0.15
    (Post
    0.15
    \Post
    0.15
     Npgsql
    0.15
    543
    0.15
     pg
    0.14
    _post
    0.14
    Activations Density 0.036%

    No Known Activations