© 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. 88000
    Prev
    Next
    INDEX
    Explanations

    references to collective action and collaboration

    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
    енÑı
    -0.07
    ning
    -0.07
    line
    -0.07
    sch
    -0.07
    mel
    -0.07
    rik
    -0.07
    ìĪł
    -0.07
    elastic
    -0.07
    uito
    -0.07
    ier
    -0.07
    POSITIVE LOGITS
    /group
    0.09
     nouns
    0.08
     memory
    0.07
    ively
    0.07
     noun
    0.07
     bargaining
    0.07
     wisdom
    0.07
     effort
    0.07
     collective
    0.07
    -sama
    0.06
    Activations Density 0.010%

    No Known Activations