© 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. 55555
    Prev
    Next
    INDEX
    Explanations

    expressions related to complexity and nuanced concepts 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
    opsis
    -0.07
    uzzi
    -0.07
     kostenlose
    -0.06
    _SHARE
    -0.06
     Breed
    -0.06
     Twin
    -0.06
    inz
    -0.06
    675
    -0.06
    rov
    -0.06
    braco
    -0.06
    POSITIVE LOGITS
     complex
    0.14
    complex
    0.12
     Complex
    0.12
     complexity
    0.12
    Complex
    0.10
    è¤ĩ
    0.10
     Complexity
    0.09
     complicated
    0.09
     complexities
    0.09
     ë³µ
    0.09
    Activations Density 0.042%

    No Known Activations