© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 15937
    Prev
    Next
    INDEX
    Explanations

    terms related to antibiotic resistance and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĢī
    -0.08
    asher
    -0.07
     ç«
    -0.07
    713
    -0.07
    паÑĤ
    -0.07
    ãĦ
    -0.07
    eneg
    -0.07
    å§ĵ
    -0.07
    ÄĽk
    -0.07
     thái
    -0.06
    POSITIVE LOGITS
     resistant
    0.07
     hospital
    0.07
    akter
    0.06
     hospitals
    0.06
     Hospital
    0.06
    issy
    0.06
    yx
    0.06
     nos
    0.06
     Hospitals
    0.06
     antibiotic
    0.06
    Activations Density 0.014%

    No Known Activations