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

    Neuronpedia

    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. 40019
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to heart conditions and their treatment

    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
    perms
    -0.07
    axed
    -0.07
    BOSE
    -0.07
    ZO
    -0.06
     imm
    -0.06
    عÙĦ
    -0.06
     Jenner
    -0.06
     Amnesty
    -0.06
     اÙĦÙħÙĩ
    -0.06
    ãĥ«ãĤ¯
    -0.06
    POSITIVE LOGITS
     cardiac
    0.11
    card
    0.11
     Heart
    0.10
     heart
    0.10
     Card
    0.10
     myocard
    0.10
    Heart
    0.10
     Cardio
    0.09
    CARD
    0.09
     hearts
    0.09
    Activations Density 0.012%

    No Known Activations