© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 104114
    Prev
    Next
    INDEX
    Explanations

    elements related to policies and regulations affecting healthcare coverage

    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
    imson
    -0.08
    undry
    -0.08
    chwitz
    -0.07
    undler
    -0.07
    iffies
    -0.07
    ctal
    -0.07
    Ñĩин
    -0.07
    oling
    -0.07
    imes
    -0.07
    akis
    -0.06
    POSITIVE LOGITS
     vital
    0.09
     important
    0.08
     integral
    0.07
     crucial
    0.07
    ero
    0.07
     essential
    0.07
     source
    0.07
     abrupt
    0.07
    ,
    0.07
     relied
    0.06
    Activations Density 0.238%

    No Known Activations