© 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 EvalsExportsinterp-engineNEWAPI 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. 107919
    Prev
    Next
    INDEX
    Explanations

    elements related to multiple sclerosis and its effects on health

    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
    iren
    -0.07
     ostr
    -0.06
    .pag
    -0.06
     wart
    -0.06
     Sco
    -0.06
     Estr
    -0.06
    æ£
    -0.06
     cooperative
    -0.05
    entials
    -0.05
     ìļĶ
    -0.05
    POSITIVE LOGITS
    NewProp
    0.08
    @nate
    0.07
    flamm
    0.07
    íĨłíĨł
    0.07
    EmptyEntries
    0.07
    amage
    0.07
    Nuitka
    0.07
     cell
    0.07
    .Named
    0.07
    OffsetTable
    0.07
    Activations Density 0.038%

    No Known Activations