© 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. 75311
    Prev
    Next
    INDEX
    Explanations

    discussions related to healthcare management and nurse staffing decisions

    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
     doctors
    -0.07
    increment
    -0.06
    mw
    -0.06
    ugi
    -0.06
    isman
    -0.06
     —
    -0.06
    ums
    -0.06
    дом
    -0.06
    виж
    -0.06
     Bil
    -0.05
    POSITIVE LOGITS
    orners
    0.07
    缤
    0.07
    âĻª
    0.07
    qli
    0.07
    Parm
    0.06
    ertools
    0.06
    CCA
    0.06
     dahi
    0.06
     Consort
    0.06
    Įĵ
    0.06
    Activations Density 0.001%

    No Known Activations