© 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. 82924
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and patient care 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
    ?type
    -0.07
     pornos
    -0.07
    aspect
    -0.06
    ecast
    -0.06
    NESS
    -0.06
    ÐĶÐļ
    -0.06
    linkplain
    -0.06
     okres
    -0.06
    ê·¹
    -0.06
    lrt
    -0.06
    POSITIVE LOGITS
    -init
    0.09
    acher
    0.08
     efforts
    0.07
    -origin
    0.07
    -led
    0.07
     effort
    0.07
     involvement
    0.07
    agal
    0.07
    -owned
    0.07
    ongyang
    0.07
    Activations Density 0.129%

    No Known Activations