© 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. 28843
    Prev
    Next
    INDEX
    Explanations

    health-related measurements and vital signs

    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
    ãĥ¼ãĥĢ
    -0.07
    icious
    -0.07
    γκα
    -0.07
    ddit
    -0.06
    apons
    -0.06
    ë¥ĺ
    -0.06
     Progressive
    -0.06
     Shelter
    -0.06
    ienne
    -0.06
    mith
    -0.06
    POSITIVE LOGITS
     temperature
    0.08
     fever
    0.08
     Fever
    0.08
     temperatures
    0.07
     Temperature
    0.07
    Ñįн
    0.07
     luk
    0.06
    READING
    0.06
     Fahrenheit
    0.06
     accurate
    0.06
    Activations Density 0.003%

    No Known Activations