© 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 EvalsExportsAPI 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. 71256
    Prev
    Next
    INDEX
    Explanations

    terms related to hospice care and end-of-life services

    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
    izard
    -0.07
    ypse
    -0.07
    erer
    -0.07
    zej
    -0.07
    iolet
    -0.07
    asurer
    -0.06
    istically
    -0.06
    _nsec
    -0.06
     Claud
    -0.06
    ting
    -0.06
    POSITIVE LOGITS
    sein
    0.08
    ilon
    0.08
    obox
    0.08
    kins
    0.07
    ITAL
    0.07
    i
    0.06
    etter
    0.06
    ãĥ«ãĥĪ
    0.06
    ylon
    0.06
    craft
    0.06
    Activations Density 0.003%

    No Known Activations