© 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. 75037
    Prev
    Next
    INDEX
    Explanations

    concepts related to epidemic modeling and synchronization in networks

    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
     UIB
    -0.07
    locker
    -0.07
    ddit
    -0.07
    ìłĿ
    -0.07
    ifar
    -0.07
    }());↵
    -0.07
     displacement
    -0.07
    ITE
    -0.07
    IGO
    -0.06
    SEC
    -0.06
    POSITIVE LOGITS
     exposed
    0.07
     Modeling
    0.07
     contacts
    0.07
     infected
    0.07
     infectious
    0.06
     modelling
    0.06
     Contacts
    0.06
     infection
    0.06
     modeling
    0.06
     ê°IJ
    0.06
    Activations Density 0.009%

    No Known Activations