© 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. 25644
    Prev
    Next
    INDEX
    Explanations

    providing information or instructions

    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
     bagi
    -0.17
     kepada
    -0.13
    ç»Ļ
    -0.12
    給
    -0.12
     sobie
    -0.11
     ÑģобÑĸ
    -0.11
     dÃłnh
    -0.10
    åIJij
    -0.10
     Alle
    -0.10
     vorhand
    -0.10
    POSITIVE LOGITS
     PROGMEM
    0.10
     Doch
    0.10
    781
    0.09
    arness
    0.09
     onların
    0.09
     Bo
    0.09
     Kam
    0.08
     Options
    0.08
    opolitan
    0.08
     floods
    0.08
    Activations Density 0.218%

    No Known Activations