© 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. 62345
    Prev
    Next
    INDEX
    Explanations

    implies deeper meanings

    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
     reput
    -0.09
     indeed
    -0.08
    BV
    -0.08
    INDER
    -0.08
    åħ¨éĿ¢
    -0.08
    igor
    -0.08
    agr
    -0.08
    ente
    -0.08
     Confeder
    -0.08
    bidden
    -0.08
    POSITIVE LOGITS
     blurred
    0.11
     rebut
    0.09
     pace
    0.09
     Nem
    0.09
     connections
    0.09
     cross
    0.09
     kino
    0.08
    nem
    0.08
    ziej
    0.08
     connection
    0.08
    Activations Density 0.093%

    No Known Activations