© 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. 107033
    Prev
    Next
    INDEX
    Explanations

    references to legislation and policy initiatives related to paid family and medical leave

    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
    zeich
    -0.07
    íį¼
    -0.06
    ãģĵãģĨ
    -0.06
    elin
    -0.06
     yourselves
    -0.06
    ela
    -0.06
    .Euler
    -0.06
    anka
    -0.06
    ³
    -0.06
     Gä
    -0.06
    POSITIVE LOGITS
     previous
    0.14
     earlier
    0.12
     recent
    0.11
     ones
    0.11
     Previous
    0.10
    previous
    0.10
     previously
    0.10
    Previous
    0.09
     existing
    0.09
     Earlier
    0.09
    Activations Density 0.046%

    No Known Activations