© 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. 90470
    Prev
    Next
    INDEX
    Explanations

    terms related to financial costs and fees in real estate transactions

    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
    kon
    -0.06
     Simple
    -0.06
    pond
    -0.06
    752
    -0.06
    à¹ĭ
    -0.05
    _simple
    -0.05
    -simple
    -0.05
    ìłģ
    -0.05
     Ä
    -0.05
    -index
    -0.05
    POSITIVE LOGITS
     fees
    0.07
    occo
    0.07
     pushViewController
    0.07
    .ecore
    0.07
    oose
    0.07
    bsite
    0.06
    INTR
    0.06
    etri
    0.06
    ocaly
    0.06
    oir
    0.06
    Activations Density 0.003%

    No Known Activations