© 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. 30058
    Prev
    Next
    INDEX
    Explanations

    concepts related to complexity and efficiency in processes

    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
    ieder
    -0.07
    ¶
    -0.05
    IVE
    -0.05
    ive
    -0.05
    /desktop
    -0.05
     sol
    -0.05
    ÙĪات
    -0.05
     tam
    -0.05
    çĥĪ
    -0.05
     until
    -0.05
    POSITIVE LOGITS
     Complexity
    0.08
     potentially
    0.08
     complexity
    0.07
    ÙĪرÙĨ
    0.07
    areth
    0.07
    ãĤ·ãĥ¼
    0.07
    dup
    0.07
     phức
    0.07
    /*č↵
    0.07
    اÙĨس
    0.07
    Activations Density 0.034%

    No Known Activations