© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125100
    Prev
    Next
    INDEX
    Explanations

    references to patient care, hospital operations, and emergency situations

    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
    ç£
    -0.07
    èĪĪ
    -0.06
    resse
    -0.06
    ivo
    -0.06
    UNET
    -0.06
    èħ¿
    -0.06
    ANTED
    -0.06
    _dummy
    -0.06
    åħ´
    -0.06
    ocular
    -0.05
    POSITIVE LOGITS
     suite
    0.08
     suites
    0.07
    room
    0.07
     departments
    0.07
     rooms
    0.07
     оÑĤдел
    0.07
     department
    0.07
    suite
    0.07
     Suite
    0.07
    olan
    0.07
    Activations Density 0.014%

    No Known Activations