© 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. 30291
    Prev
    Next
    INDEX
    Explanations

    issues related to systemic inefficiencies and healthcare challenges

    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
     gain
    -0.06
    èĤī
    -0.06
    adier
    -0.06
     promin
    -0.06
     proje
    -0.06
     depr
    -0.06
    itler
    -0.06
    velop
    -0.06
     Workbook
    -0.06
    ery
    -0.06
    POSITIVE LOGITS
     scl
    0.07
    egov
    0.07
    leep
    0.07
     suff
    0.06
    aeda
    0.06
     Lag
    0.06
     Rut
    0.06
    åĢī
    0.06
     uzavÅĻ
    0.06
     Baum
    0.06
    Activations Density 0.049%

    No Known Activations