© 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. 9-LLAMASCOPE-RES-131K
    11. 94738
    Prev
    Next
    INDEX
    Explanations

    terms related to caregiving and care 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
    OKIE
    -0.09
    sss
    -0.08
    mars
    -0.08
    recht
    -0.08
    -era
    -0.08
    ãĥ³ãĥĸ
    -0.07
    uario
    -0.07
    amedi
    -0.07
    shire
    -0.07
    self
    -0.07
    POSITIVE LOGITS
    fully
    0.12
    lessly
    0.09
    ÏħÏĦÏĮ
    0.07
    ìĦľëĬĶ
    0.07
    riel
    0.07
    سÙĩ
    0.07
    ynı
    0.07
    imonial
    0.07
    iche
    0.07
    lessness
    0.07
    Activations Density 0.034%

    No Known Activations