© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106205
    Prev
    Next
    INDEX
    Explanations

    mentions of earnings and income-related information

    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
    astos
    -0.07
    Äįel
    -0.07
    ERG
    -0.06
    allen
    -0.06
    ingham
    -0.06
     Energ
    -0.06
    OTES
    -0.06
     Preis
    -0.06
    OMET
    -0.06
    YLON
    -0.06
    POSITIVE LOGITS
     income
    0.10
     Income
    0.09
    Income
    0.09
     passive
    0.08
     revenue
    0.08
    -income
    0.07
     Passive
    0.07
     profit
    0.07
     incomes
    0.07
    æĶ¶åħ¥
    0.07
    Activations Density 0.012%

    No Known Activations