© 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. 105131
    Prev
    Next
    INDEX
    Explanations

    references to humanitarian aid and crisis efforts

    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
     retal
    -0.06
     noir
    -0.06
     retali
    -0.06
     Arbit
    -0.06
    ippy
    -0.06
    ãģ¡ãģ¯
    -0.06
    ulia
    -0.06
     trilogy
    -0.06
    uckle
    -0.06
    _dom
    -0.06
    POSITIVE LOGITS
     funding
    0.08
     fund
    0.08
     aid
    0.07
     contributions
    0.07
     commitments
    0.07
     Commit
    0.07
     Fund
    0.07
     funds
    0.07
     pledges
    0.07
    amount
    0.07
    Activations Density 0.013%

    No Known Activations