© 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. 9-LLAMASCOPE-RES-131K
    11. 95403
    Prev
    Next
    INDEX
    Explanations

    topics related to payment systems and subscription models

    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
    oya
    -0.07
     McCart
    -0.07
    _SUITE
    -0.06
    urve
    -0.06
    tvrt
    -0.06
    iÃŁ
    -0.06
    cak
    -0.06
     MetroFramework
    -0.06
    oo
    -0.06
    опол
    -0.06
    POSITIVE LOGITS
    usher
    0.07
    Recognizer
    0.06
    mite
    0.06
    olson
    0.06
    rozen
    0.06
     encounters
    0.06
    ']+
    0.06
    NewItem
    0.06
     Sheldon
    0.06
     encounter
    0.06
    Activations Density 0.002%

    No Known Activations