© 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
    5. 50-RESID-POST-GF
    7. 37964
    Prev
    Next
    INDEX
    Explanations

    measles outbreak

    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
     malaria
    -0.12
     Vict
    -0.11
     AIDS
    -0.11
     HIV
    -0.10
    oron
    -0.10
    ylon
    -0.10
    orman
    -0.09
     Marketable
    -0.09
    alaria
    -0.09
     Alzheimer
    -0.09
    POSITIVE LOGITS
     rub
    0.18
     pert
    0.17
     Rub
    0.16
    pert
    0.16
     Pert
    0.16
     measles
    0.15
     Me
    0.14
     chicken
    0.13
    Rub
    0.13
     susceptible
    0.12
    Activations Density 0.026%

    No Known Activations