© 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. 130250
    Prev
    Next
    INDEX
    Explanations

    references to political conflicts and human rights violations

    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
    rys
    -0.07
     Newport
    -0.07
    Race
    -0.07
     immigrant
    -0.07
     Race
    -0.07
     Nik
    -0.07
    quez
    -0.06
    appen
    -0.06
    astos
    -0.06
    iej
    -0.06
    POSITIVE LOGITS
     Uganda
    0.07
     Liberia
    0.07
     pred
    0.07
     Jong
    0.07
     African
    0.07
     Nd
    0.06
    DBG
    0.06
     Africa
    0.06
     Sierra
    0.06
     Ug
    0.06
    Activations Density 0.005%

    No Known Activations