© 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 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. 71181
    Prev
    Next
    INDEX
    Explanations

    concepts associated with collaboration and coordination in various 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
    ichen
    -0.08
    buch
    -0.08
    ätz
    -0.07
    ायन
    -0.07
    idian
    -0.07
    inth
    -0.07
     WRONG
    -0.07
    iš
    -0.07
     именно
    -0.07
    isman
    -0.07
    POSITIVE LOGITS
    /shared
    0.10
     between
    0.10
     approach
    0.08
    between
    0.08
     shared
    0.08
     Between
    0.07
     across
    0.07
     Shared
    0.07
     effort
    0.07
    /Common
    0.07
    Activations Density 0.065%

    No Known Activations