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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27638
    Prev
    Next
    INDEX
    Explanations

    references to gameplay mechanics and enemy interactions in video 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
    _axes
    -0.08
     strav
    -0.07
    hma
    -0.07
    uild
    -0.07
    ãĤĩãģĨ
    -0.07
    ynos
    -0.07
    rzy
    -0.07
    PLL
    -0.07
    _MAGIC
    -0.07
    ndl
    -0.07
    POSITIVE LOGITS
     enemy
    0.07
     scripted
    0.06
    iff
    0.06
     groups
    0.06
     types
    0.06
    ajo
    0.06
     enemies
    0.06
    OfType
    0.06
    cons
    0.05
     varieties
    0.05
    Activations Density 0.021%

    No Known Activations