© 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. 93026
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical research and treatments

    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
     è©
    -0.07
    orz
    -0.07
    ensual
    -0.06
    ihad
    -0.06
    indrome
    -0.06
    лÑĭ
    -0.06
    cela
    -0.06
    ledon
    -0.06
    Permanent
    -0.06
    ensa
    -0.06
    POSITIVE LOGITS
    oldt
    0.07
     hopefully
    0.07
     reviewed
    0.07
    CURRENT
    0.07
    review
    0.07
     mechan
    0.07
    (concat
    0.07
    -current
    0.07
    -review
    0.07
    _reviews
    0.07
    Activations Density 0.017%

    No Known Activations