© 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. 17-LLAMASCOPE-RES-131K
    11. 17232
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty and complexity in situations

    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
    ani
    -0.06
    .minimum
    -0.06
     Bans
    -0.06
    Minimum
    -0.06
    enet
    -0.06
     particul
    -0.06
    ANI
    -0.06
     Ladies
    -0.06
    ek
    -0.06
    argin
    -0.06
    POSITIVE LOGITS
     majority
    0.29
     Majority
    0.22
     болÑĮÑĪин
    0.21
     meisten
    0.18
     ëĮĢë¶Ģë¶Ħ
    0.17
     vÄĽtÅ¡
    0.17
     mayorÃŃa
    0.17
     most
    0.17
     MOST
    0.15
     vast
    0.14
    Activations Density 0.166%

    No Known Activations