© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4063
    Prev
    Next
    INDEX
    Explanations

    information related to wealth and financial status

    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
    inker
    -0.08
    enser
    -0.07
    Forgery
    -0.07
    ENCY
    -0.07
     sm
    -0.07
    ERC
    -0.07
    ras
    -0.06
    atori
    -0.06
    izzo
    -0.06
    baugh
    -0.06
    POSITIVE LOGITS
     richest
    0.06
    á»Ŀ
    0.06
    orders
    0.06
    dde
    0.06
     Ree
    0.06
     Mans
    0.06
    ,'%
    0.06
     Ultra
    0.06
     richer
    0.06
     mans
    0.06
    Activations Density 0.005%

    No Known Activations