© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 36263
    Prev
    Next
    INDEX
    Explanations

    and health

    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
     diarr
    -0.12
     çĹ
    -0.12
     diarrhea
    -0.11
     headache
    -0.10
     vul
    -0.09
    acco
    -0.09
     disabling
    -0.09
     dys
    -0.09
     Riley
    -0.09
     infectious
    -0.09
    POSITIVE LOGITS
     condition
    0.11
     tests
    0.11
     teÅŁ
    0.10
     regime
    0.10
    odox
    0.10
    ail
    0.09
     dosage
    0.09
     Tests
    0.09
     XR
    0.09
     dormant
    0.09
    Activations Density 0.147%

    No Known Activations