© 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. 15-LLAMASCOPE-RES-131K
    11. 249
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and financial obligations, specifically in the context of bonding and insurance

    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
    ervo
    -0.08
    coni
    -0.08
    istrovstvÃŃ
    -0.07
    «
    -0.07
    неÑģ
    -0.07
    NSNotification
    -0.07
    âĸ¡âĸ¡
    -0.07
    ãĤīãģĹ
    -0.07
    iÄĩ
    -0.07
    ARSER
    -0.06
    POSITIVE LOGITS
     required
    0.07
     quotes
    0.06
     recourse
    0.06
     Required
    0.06
     quote
    0.06
     coverage
    0.06
    required
    0.06
     agent
    0.06
     needed
    0.06
     Sec
    0.06
    Activations Density 0.002%

    No Known Activations