© 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. 17-LLAMASCOPE-RES-131K
    6. 83794
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to medical and health data analysis

    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
    '](
    -0.07
    {}
    -0.06
    "](
    -0.06
    iferay
    -0.06
    اÙĦات
    -0.06
    abet
    -0.06
    uest
    -0.06
    CompanyName
    -0.05
    Thunk
    -0.05
    ãĢįï¼Ī
    -0.05
    POSITIVE LOGITS
    .bunifuFlatButton
    0.07
    ãģ¨ãĤĤ
    0.07
     ØĽ
    0.07
    ãģĽãĤĭ
    0.06
    LastError
    0.06
    ÙĨاÙĨ
    0.06
    áŀ¶
    0.06
    UpInside
    0.06
    .Guna
    0.06
    chy
    0.06
    Activations Density 0.013%

    No Known Activations