© 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. 1605
    Prev
    Next
    INDEX
    Explanations

    references to healthcare organizations and related entities

    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
     Carp
    -0.07
     Feld
    -0.06
    uckland
    -0.06
    inceton
    -0.06
     Cornell
    -0.06
     fucked
    -0.06
     correspond
    -0.06
    æľĹ
    -0.06
     fuck
    -0.06
    важ
    -0.06
    POSITIVE LOGITS
    orsk
    0.08
     ÑĥÑģ
    0.07
     ÙħتÙĨ
    0.07
    usch
    0.07
     تÙĪÙħ
    0.07
    ippi
    0.07
    ahoma
    0.07
     Missouri
    0.06
    innacle
    0.06
     Memphis
    0.06
    Activations Density 0.000%

    No Known Activations