© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61597
    Prev
    Next
    INDEX
    Explanations

    medical professionals and institutions related to healthcare

    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
    uling
    -0.07
    igate
    -0.07
    shelf
    -0.07
    strap
    -0.07
     sense
    -0.06
    uran
    -0.06
    ritz
    -0.06
     fitte
    -0.06
    adian
    -0.06
    erals
    -0.06
    POSITIVE LOGITS
    ãĤī
    0.07
    .Autowired
    0.07
     Sands
    0.06
    .icons
    0.06
    otos
    0.06
    §
    0.06
     vụ
    0.06
    ushima
    0.06
    ожеÑĤ
    0.06
     nos
    0.06
    Activations Density 0.031%

    No Known Activations