© 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. 3441
    Prev
    Next
    INDEX
    Explanations

    references to labor movements and strikes

    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
    ombo
    -0.07
    CADE
    -0.07
    edu
    -0.07
    wake
    -0.07
    etz
    -0.06
    quee
    -0.06
    íĸ¥
    -0.06
     Fiscal
    -0.06
    Ä±ÅŁÄ±k
    -0.06
    à¸ļาà¸Ĺ
    -0.06
    POSITIVE LOGITS
     strike
    0.07
    -temp
    0.07
     union
    0.06
     pick
    0.06
     temps
    0.06
     temp
    0.06
     striker
    0.06
    sy
    0.06
     Frederick
    0.06
    857
    0.06
    Activations Density 0.007%

    No Known Activations