© 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 EvalsExportsinterp-engineNEWAPI 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. 14741
    Prev
    Next
    INDEX
    Explanations

    mentions of oversight and accountability in relation to fraud and security

    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
    loff
    -0.07
    /Peak
    -0.07
    nak
    -0.07
    梨
    -0.07
    _mD
    -0.07
     Haupt
    -0.07
    ħn
    -0.07
    دارÛĮ
    -0.07
    MethodImpl
    -0.07
    OffsetTable
    -0.07
    POSITIVE LOGITS
     checks
    0.14
    checks
    0.12
     vet
    0.12
     Checks
    0.11
     controls
    0.11
     check
    0.10
    -check
    0.10
     checking
    0.10
    Checks
    0.09
     risk
    0.09
    Activations Density 0.059%

    No Known Activations