© 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
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 56918
    Prev
    Next
    INDEX
    Explanations

    cassandra database

    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
    rais
    -0.12
     Civic
    -0.10
     Hond
    -0.10
     Tur
    -0.09
     Sw
    -0.09
    741
    -0.09
     Birmingham
    -0.09
     Canterbury
    -0.09
    CharArray
    -0.09
     soy
    -0.09
    POSITIVE LOGITS
     cass
    0.17
    assandra
    0.17
     Cassandra
    0.16
     Cass
    0.13
    andra
    0.13
     Colombia
    0.13
     Nova
    0.12
     Columbia
    0.11
     Arlington
    0.11
     Saturn
    0.11
    Activations Density 0.039%

    No Known Activations