© 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. 86702
    Prev
    Next
    INDEX
    Explanations

    specific medical conditions and their prevalence in various populations

    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
    liž
    -0.08
     registrazione
    -0.08
    venes
    -0.07
    jeme
    -0.07
    esser
    -0.07
    leme
    -0.07
    ucer
    -0.07
    ardin
    -0.06
    ÅĻez
    -0.06
    veis
    -0.06
    POSITIVE LOGITS
     individuals
    0.09
    844
    0.08
     humans
    0.07
     conc
    0.07
     patients
    0.07
    566
    0.06
     persons
    0.06
     Humans
    0.06
    ighthouse
    0.06
    atoi
    0.06
    Activations Density 0.066%

    No Known Activations