© 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. 14689
    Prev
    Next
    INDEX
    Explanations

    terms related to palliative and hospice care

    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
    olie
    -0.08
    ITIES
    -0.08
    ingle
    -0.07
    sdale
    -0.07
    Disappear
    -0.07
    INGS
    -0.07
    ings
    -0.07
    ENCIL
    -0.07
    toa
    -0.07
    iyim
    -0.07
    POSITIVE LOGITS
     pall
    0.09
     services
    0.08
     care
    0.08
     terminal
    0.07
    /end
    0.07
     Pall
    0.07
    GLOSS
    0.06
     Final
    0.06
     Terminal
    0.06
    agonal
    0.06
    Activations Density 0.003%

    No Known Activations