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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78248
    Prev
    Next
    INDEX
    Explanations

    references to historical pandemics and diseases

    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
    apiro
    -0.07
     Evet
    -0.07
    /Instruction
    -0.07
    ntl
    -0.07
    idlo
    -0.07
    olie
    -0.07
    afc
    -0.07
    imestone
    -0.07
    éģŃ
    -0.07
    ÂłkW
    -0.06
    POSITIVE LOGITS
     death
    0.07
     deaths
    0.06
     population
    0.06
     mort
    0.06
     demographic
    0.06
     disease
    0.06
     mortality
    0.06
     dep
    0.06
     mass
    0.06
     toll
    0.06
    Activations Density 0.015%

    No Known Activations