© 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. 39237
    Prev
    Next
    INDEX
    Explanations

    medical history and conditions related to chronic illnesses and family background

    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
    ãĥ¼ãĥĢ
    -0.08
    errer
    -0.07
    ÃľRK
    -0.07
    743
    -0.07
    гоÑĤ
    -0.07
    æī£
    -0.07
     accru
    -0.07
     dosp
    -0.07
    insk
    -0.07
    елик
    -0.07
    POSITIVE LOGITS
     previous
    0.09
     previously
    0.08
    Previous
    0.08
     Previous
    0.08
    à¹Ģà¸Ħย
    0.07
    /current
    0.07
    previous
    0.07
     history
    0.06
    lund
    0.06
     never
    0.06
    Activations Density 0.014%

    No Known Activations