© 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. 119377
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic and medical testing, particularly cancer screening

    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
     Rosenstein
    -0.08
    Ïģα
    -0.08
    GenerationStrategy
    -0.07
    nio
    -0.07
     Resume
    -0.07
    usercontent
    -0.07
    /XMLSchema
    -0.07
    inters
    -0.07
    olk
    -0.07
     DISPATCH
    -0.07
    POSITIVE LOGITS
     check
    0.09
     test
    0.08
     checks
    0.08
     tests
    0.08
    leigh
    0.08
     analysis
    0.07
     checked
    0.06
     consultation
    0.06
     screening
    0.06
     specialist
    0.06
    Activations Density 0.033%

    No Known Activations