© 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. 80003
    Prev
    Next
    INDEX
    Explanations

    terms related to accountable care organizations and healthcare systems

    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
    HEST
    -0.07
     Cres
    -0.07
    SEG
    -0.06
    bia
    -0.06
    esen
    -0.06
    estre
    -0.06
    apr
    -0.06
    antha
    -0.06
    aign
    -0.06
    éijij
    -0.06
    POSITIVE LOGITS
     Longitude
    0.09
    .cms
    0.07
     pilots
    0.07
     ÑĥÑĩаÑģ
    0.07
     penalties
    0.07
     Medicare
    0.07
     participating
    0.06
    862
    0.06
     pilot
    0.06
     programmes
    0.06
    Activations Density 0.008%

    No Known Activations