© 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. 74472
    Prev
    Next
    INDEX
    Explanations

    instances of group dynamics and interactions among individuals

    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
    IfNeeded
    -0.07
     vielen
    -0.07
     czÄĻ
    -0.07
    usk
    -0.06
     muit
    -0.06
    orer
    -0.06
     many
    -0.06
    aset
    -0.06
    ubic
    -0.06
    æĴ
    -0.06
    POSITIVE LOGITS
     recent
    0.08
     lately
    0.07
     recently
    0.07
     consecutive
    0.07
     already
    0.07
    åĪĨåĪ«
    0.07
     tonight
    0.07
     directly
    0.07
     myself
    0.06
     DIRECT
    0.06
    Activations Density 0.041%

    No Known Activations