© 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. 17-LLAMASCOPE-RES-131K
    11. 125975
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures and cardiovascular health

    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
    pager
    -0.06
    IClient
    -0.06
    -valid
    -0.06
    abad
    -0.06
    coli
    -0.06
     Incoming
    -0.06
    (fun
    -0.06
    -addon
    -0.06
    akk
    -0.06
    oup
    -0.06
    POSITIVE LOGITS
     balloon
    0.09
     angi
    0.08
     cath
    0.08
     artery
    0.07
     card
    0.07
     Cath
    0.07
     guid
    0.07
     Cardio
    0.07
     coronary
    0.07
     Coron
    0.07
    Activations Density 0.011%

    No Known Activations