© 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. 104368
    Prev
    Next
    INDEX
    Explanations

    terms related to fraud and financial misconduct

    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
    .scalablytyped
    -0.10
    GuidId
    -0.08
    actionDate
    -0.08
    ÑĤаб
    -0.07
    ä¿ĿéĻ©
    -0.07
    /stdc
    -0.07
    tu
    -0.07
    _Tis
    -0.07
    λιο
    -0.07
    assi
    -0.07
    POSITIVE LOGITS
     fake
    0.07
     fraud
    0.07
    phant
    0.07
     phantom
    0.07
     ghost
    0.07
     reporting
    0.07
     reported
    0.07
     claimed
    0.07
     Reporting
    0.06
    ks
    0.06
    Activations Density 0.101%

    No Known Activations