© 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. 57609
    Prev
    Next
    INDEX
    Explanations

    rapid blood transfusion

    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
     Vaccine
    -0.09
     airflow
    -0.09
     urinary
    -0.08
    hotmail
    -0.08
     sog
    -0.08
    oir
    -0.08
    _mtime
    -0.08
     onHide
    -0.08
     Netz
    -0.08
     Tom
    -0.08
    POSITIVE LOGITS
     blood
    0.50
     Blood
    0.44
    Blood
    0.38
    è¡Ģ
    0.36
    blood
    0.36
     transf
    0.35
    -blood
    0.33
     кÑĢови
    0.28
     máu
    0.28
     plasma
    0.27
    Activations Density 0.046%

    No Known Activations