© 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. 39219
    Prev
    Next
    INDEX
    Explanations

    listing types and categories

    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
    ships
    -0.09
     Classified
    -0.09
     classified
    -0.08
     Variant
    -0.08
     variant
    -0.08
     subsidiaries
    -0.08
    849
    -0.08
     Trab
    -0.08
    856
    -0.08
     submarines
    -0.08
    POSITIVE LOGITS
     categories
    0.48
     category
    0.45
     types
    0.41
     Categories
    0.35
    Categories
    0.33
     каÑĤегоÑĢ
    0.33
    categories
    0.32
    category
    0.31
     categorie
    0.30
     type
    0.30
    Activations Density 0.294%

    No Known Activations