© 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. 71835
    Prev
    Next
    INDEX
    Explanations

    phrases related to activism and social justice issues

    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
    quirrel
    -0.07
    ãĥ³ãĥij
    -0.07
    claimer
    -0.06
    sob
    -0.06
    ÏĦικα
    -0.06
     kontakte
    -0.06
    ntax
    -0.06
    IRCLE
    -0.06
     stos
    -0.06
    irth
    -0.06
    POSITIVE LOGITS
     boycott
    0.07
     decision
    0.07
     company
    0.07
    ahas
    0.07
     Decision
    0.06
     business
    0.06
     indirect
    0.06
     companies
    0.06
     pressure
    0.06
     corporate
    0.06
    Activations Density 0.013%

    No Known Activations