© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 103965
    Prev
    Next
    INDEX
    Explanations

    references to solo gameplay and narrative elements in games

    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
    صÙģ
    -0.07
    echa
    -0.07
    hiba
    -0.06
     Ung
    -0.06
     cán
    -0.06
    zin
    -0.06
    uries
    -0.06
     Porno
    -0.06
    amaz
    -0.06
    weets
    -0.06
    POSITIVE LOGITS
    ucker
    0.07
    ignon
    0.07
     narrative
    0.07
    lo
    0.06
     narratives
    0.06
    /story
    0.06
     Pastor
    0.06
    ogh
    0.06
    oplevel
    0.06
     -*-č↵
    0.06
    Activations Density 0.008%

    No Known Activations