© 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. 30293
    Prev
    Next
    INDEX
    Explanations

    gases and chemical compounds

    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
     chemical
    -0.13
     chemistry
    -0.12
     oxy
    -0.10
    chemical
    -0.10
     chem
    -0.10
     chemicals
    -0.10
    RTL
    -0.10
    oxid
    -0.10
    chemistry
    -0.10
     Chemistry
    -0.09
    POSITIVE LOGITS
     testosterone
    0.14
     carbon
    0.14
     glucose
    0.13
     caffeine
    0.12
     CO
    0.12
     heroine
    0.12
     serotonin
    0.12
     adrenaline
    0.12
     iron
    0.11
     water
    0.11
    Activations Density 0.103%

    No Known Activations