© 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. 33888
    Prev
    Next
    INDEX
    Explanations

    prevent tooth decay or address deficiencies

    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
    mares
    -0.09
     ammonia
    -0.09
     degraded
    -0.09
     carbon
    -0.09
     Reward
    -0.09
     methane
    -0.08
     Malta
    -0.08
     Batt
    -0.08
     saints
    -0.08
     substituted
    -0.08
    POSITIVE LOGITS
     iod
    0.27
    iod
    0.17
     thyroid
    0.15
     salt
    0.13
     fort
    0.13
    fort
    0.12
     IDD
    0.12
    thy
    0.11
     Kash
    0.11
     thy
    0.11
    Activations Density 0.020%

    No Known Activations