© 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. 17-LLAMASCOPE-RES-131K
    11. 76353
    Prev
    Next
    INDEX
    Explanations

    instances of group dynamics and social interactions

    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
    ouro
    -0.07
    à¤łà¤¨
    -0.07
    aggio
    -0.07
    yon
    -0.07
    berman
    -0.07
    Ïģά
    -0.07
    ertas
    -0.06
     recently
    -0.06
     componentName
    -0.06
    ocommerce
    -0.06
    POSITIVE LOGITS
     Soon
    0.07
     soon
    0.07
    vo
    0.07
    ModelError
    0.06
     estar
    0.06
    riere
    0.06
     ready
    0.06
     already
    0.06
    RLF
    0.06
     wonder
    0.06
    Activations Density 0.090%

    No Known Activations