© 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. 35001
    Prev
    Next
    INDEX
    Explanations

    antibiotic resistance and treatment

    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
    annel
    -0.09
    ounds
    -0.09
    phas
    -0.08
    cel
    -0.08
    sters
    -0.08
    ãĢħ
    -0.08
    stract
    -0.08
    fulness
    -0.08
    gi
    -0.08
    orph
    -0.08
    POSITIVE LOGITS
     resistance
    0.12
    -resistant
    0.12
     Resistance
    0.11
     steward
    0.11
     Fleming
    0.10
    Resistance
    0.10
    uo
    0.10
    ello
    0.09
    acterial
    0.09
    ics
    0.09
    Activations Density 0.020%

    No Known Activations