© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3786
    Prev
    Next
    INDEX
    Explanations

    words related to danger and risks

    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
    istory
    -0.08
     my
    -0.07
    让æĪij
    -0.07
     maybe
    -0.07
     saya
    -0.06
    .nano
    -0.06
    seau
    -0.06
    tester
    -0.06
    à¸ļาล
    -0.06
    ãĢĤæĪij
    -0.06
    POSITIVE LOGITS
     âĹ
    0.10
     {{
    0.09
     Nobody
    0.07
     "{{
    0.07
     trope
    0.07
     ([[
    0.06
    kovÄĽ
    0.06
     DependencyProperty
    0.06
    ibia
    0.06
    ifact
    0.06
    Activations Density 0.003%

    No Known Activations