© 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. 103557
    Prev
    Next
    INDEX
    Explanations

    references to significant business transactions and contracts

    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
    δί
    -0.07
    itution
    -0.06
     secondary
    -0.06
    asurable
    -0.06
    κολ
    -0.06
    ownt
    -0.06
    ailable
    -0.06
    deo
    -0.06
    ượng
    -0.06
    á»Ļi
    -0.06
    POSITIVE LOGITS
    omers
    0.07
    ìŀIJìĿ¸
    0.06
     Customers
    0.06
    à¥ģà¤ĸ
    0.06
     customers
    0.06
    lah
    0.06
    neider
    0.06
    顾
    0.06
    éru
    0.06
     Commands
    0.06
    Activations Density 0.008%

    No Known Activations