© 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. 9-LLAMASCOPE-RES-131K
    11. 97506
    Prev
    Next
    INDEX
    Explanations

    instances of medical diagnoses and treatment data

    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
    esteem
    -0.07
    allet
    -0.07
    éł
    -0.07
     nek
    -0.07
    ãĤĥ
    -0.07
    hal
    -0.06
    edi
    -0.06
    rale
    -0.06
    etine
    -0.06
    uft
    -0.06
    POSITIVE LOGITS
    eydi
    0.07
     exclusively
    0.06
     Benson
    0.06
    utow
    0.06
    вÑĸлÑĮ
    0.06
    olkien
    0.06
    ipse
    0.06
    .operations
    0.06
    ãĥ¼ãĥ«ãĥī
    0.06
    576
    0.06
    Activations Density 0.012%

    No Known Activations