© 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. 15-LLAMASCOPE-RES-131K
    11. 89083
    Prev
    Next
    INDEX
    Explanations

    programming-related concepts and operations involving numbers and mathematical functions

    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
    ãĤĤãģĨ
    -0.08
    ¶Į
    -0.08
    Fuse
    -0.08
    акÑģим
    -0.08
    öy
    -0.08
    Ðİ
    -0.08
    å±
    -0.07
    ÑĤик
    -0.07
     Beled
    -0.07
    ToLocal
    -0.07
    POSITIVE LOGITS
    ëĭĪëĭ¤
    0.06
    587
    0.06
    111
    0.06
    /Framework
    0.06
    ake
    0.05
     nut
    0.05
    ÃŃt
    0.05
     Phaser
    0.05
    éĽ
    0.05
     wheel
    0.05
    Activations Density 0.001%

    No Known Activations