© 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. 103658
    Prev
    Next
    INDEX
    Explanations

    terms associated with health and resource management in gaming contexts

    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
    rir
    -0.07
    struction
    -0.07
    oplan
    -0.07
    istrat
    -0.06
    amma
    -0.06
    benh
    -0.06
    jam
    -0.06
    ods
    -0.06
    eken
    -0.06
    argas
    -0.06
    POSITIVE LOGITS
    ibble
    0.07
    عا
    0.07
     recover
    0.07
     Marvin
    0.06
    ,cp
    0.06
     recovery
    0.06
     Barry
    0.06
     íļĮ
    0.06
     Recover
    0.06
    ufen
    0.06
    Activations Density 0.012%

    No Known Activations