© 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. 85170
    Prev
    Next
    INDEX
    Explanations

    references to patients and healthcare-related contexts

    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
    ussen
    -0.08
    ¶Į
    -0.07
    ulas
    -0.07
    .Formatter
    -0.07
    resden
    -0.07
    reserve
    -0.07
    Decoration
    -0.07
    ucas
    -0.07
    $MESS
    -0.07
     háºŃu
    -0.07
    POSITIVE LOGITS
     use
    0.10
     existence
    0.08
     establishment
    0.07
     introduction
    0.07
     return
    0.07
     creation
    0.06
     collapse
    0.06
     demise
    0.06
    tle
    0.06
     conclusion
    0.06
    Activations Density 0.055%

    No Known Activations