© 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 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. 58860
    Prev
    Next
    INDEX
    Explanations

    medical details related to patient treatment and conditions

    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
    rette
    -0.08
     Indo
    -0.07
    itational
    -0.07
     POV
    -0.07
    reate
    -0.07
     moden
    -0.06
    oner
    -0.06
    -basic
    -0.06
    plit
    -0.06
     DEAD
    -0.06
    POSITIVE LOGITS
     tomorrow
    0.08
     yesterday
    0.07
     sched
    0.07
    obel
    0.07
    Yesterday
    0.07
     Yesterday
    0.07
     today
    0.06
    ennes
    0.06
    æĽ²
    0.06
     Fame
    0.06
    Activations Density 0.008%

    No Known Activations