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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30467
    Prev
    Next
    INDEX
    Explanations

    references to health-related incidents or outbreaks

    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
    afil
    -0.08
    dez
    -0.07
    iring
    -0.07
     sav
    -0.07
    asl
    -0.07
    ascript
    -0.07
     savory
    -0.07
    IRTH
    -0.07
    baum
    -0.07
    icer
    -0.07
    POSITIVE LOGITS
     confirmed
    0.08
     case
    0.08
    confirmed
    0.08
     confirmation
    0.07
     cases
    0.07
     Case
    0.07
     confirm
    0.07
     announced
    0.07
    éĻ¢
    0.06
     report
    0.06
    Activations Density 0.028%

    No Known Activations