© 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. 59773
    Prev
    Next
    INDEX
    Explanations

    references to legislative actions and policies related to family 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
    htub
    -0.07
    abd
    -0.07
    cona
    -0.07
    _ISO
    -0.06
    pole
    -0.06
    ienne
    -0.06
    phinx
    -0.06
    ullivan
    -0.06
    )animated
    -0.06
    lexible
    -0.06
    POSITIVE LOGITS
     House
    0.08
     cos
    0.08
     bills
    0.08
     companion
    0.08
     bill
    0.07
     sponsorship
    0.07
     sponsor
    0.07
    0.07
     legislation
    0.07
     Companion
    0.07
    Activations Density 0.051%

    No Known Activations