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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45401
    Prev
    Next
    INDEX
    Explanations

    Lactobacillus casei bacteria

    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
     antim
    -0.12
     Infect
    -0.11
    erah
    -0.10
     infectious
    -0.10
     microbial
    -0.10
     infected
    -0.09
     mac
    -0.09
    ares
    -0.09
     anth
    -0.09
    _boot
    -0.09
    POSITIVE LOGITS
     strain
    0.19
     strains
    0.18
     bacteria
    0.15
     Sac
    0.13
     ye
    0.13
     yeast
    0.13
     cells
    0.12
     Brady
    0.12
    strain
    0.12
     cultures
    0.12
    Activations Density 0.049%

    No Known Activations