© 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. 16810
    Prev
    Next
    INDEX
    Explanations

    thyroid related terms after assistant

    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
    cott
    -0.10
     Stanton
    -0.10
     Steele
    -0.10
    ï¼¾
    -0.10
     tram
    -0.09
    éĢļ
    -0.09
     trom
    -0.09
     Gilles
    -0.09
     é¦
    -0.09
    eria
    -0.08
    POSITIVE LOGITS
     thyroid
    0.30
     iod
    0.24
    thy
    0.23
     thy
    0.23
     Thy
    0.23
     Graves
    0.21
    iod
    0.19
     euth
    0.18
    çĶ²
    0.17
    othy
    0.16
    Activations Density 0.016%

    No Known Activations