© 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. 129296
    Prev
    Next
    INDEX
    Explanations

    references to "The Sims" video game series

    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
     æ®
    -0.07
    ersonic
    -0.07
     Rao
    -0.07
     Erotik
    -0.06
    spor
    -0.06
    äºŃ
    -0.06
    ovice
    -0.06
     Gaming
    -0.06
     Král
    -0.06
    uge
    -0.06
    POSITIVE LOGITS
     Sims
    0.10
     Snap
    0.07
    iesen
    0.06
    ái
    0.06
    editable
    0.06
     Snapshot
    0.06
    ĥn
    0.06
    ään
    0.06
     Cra
    0.06
    apore
    0.06
    Activations Density 0.013%

    No Known Activations