© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44538
    Prev
    Next
    INDEX
    Explanations

    medical treatments and patients

    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
     medically
    -0.11
     infra
    -0.09
     outpatient
    -0.09
     Pediatric
    -0.09
     decre
    -0.09
     clinically
    -0.09
    ancia
    -0.09
     Tib
    -0.09
     incom
    -0.09
     Yer
    -0.09
    POSITIVE LOGITS
     patient
    0.20
     Patient
    0.14
     drug
    0.12
     patience
    0.11
    Patient
    0.11
     treatments
    0.11
     paciente
    0.10
     treatment
    0.10
     disease
    0.10
    patient
    0.10
    Activations Density 0.045%

    No Known Activations