© 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. 118328
    Prev
    Next
    INDEX
    Explanations

    terms related to health, safety, and well-being in various contexts

    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
    acht
    -0.07
     ÑģвеÑĢ
    -0.07
    otte
    -0.06
    šti
    -0.06
    bos
    -0.06
    epy
    -0.06
    XP
    -0.06
    izmet
    -0.06
    /sn
    -0.06
     Sach
    -0.06
    POSITIVE LOGITS
    794
    0.07
    alling
    0.07
    aeda
    0.06
    owel
    0.06
     functioning
    0.06
    uli
    0.06
    849
    0.06
    uture
    0.06
    ASET
    0.06
    321
    0.06
    Activations Density 0.019%

    No Known Activations