© 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. 33636
    Prev
    Next
    INDEX
    Explanations

    role of viruses

    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
     microbes
    -0.11
     bacteria
    -0.11
     ADM
    -0.11
     puls
    -0.11
     Clarkson
    -0.09
     microbi
    -0.09
     microbial
    -0.09
     antibiotic
    -0.09
    allele
    -0.09
    Compound
    -0.09
    POSITIVE LOGITS
     caps
    0.23
     host
    0.22
     viral
    0.21
     vir
    0.20
     vi
    0.19
     hosts
    0.17
     Host
    0.17
     Vir
    0.17
    -host
    0.16
     hij
    0.16
    Activations Density 0.048%

    No Known Activations