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

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 87960
    Prev
    Next
    INDEX
    Explanations

    language related to policies and regulations concerning safety and well-being

    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
     Abstract
    -0.08
    Abstract
    -0.07
    vrier
    -0.07
    ubre
    -0.07
    rek
    -0.06
    metry
    -0.06
    MainFrame
    -0.06
    apas
    -0.06
    interopRequire
    -0.06
    cimal
    -0.06
    POSITIVE LOGITS
    ä¸ĸç´Ģ
    0.06
    iske
    0.06
     seks
    0.06
    ãĥ¼ãĥĨ
    0.06
     ç«
    0.06
    Ñĥж
    0.06
    alu
    0.06
    witch
    0.06
    çħ¤
    0.06
     Saf
    0.06
    Activations Density 0.001%

    No Known Activations