© 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. 17-LLAMASCOPE-RES-131K
    11. 74541
    Prev
    Next
    INDEX
    Explanations

    issues related to basic human needs and rights, particularly food and water access

    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
     moci
    -0.07
    aucoup
    -0.07
    ivec
    -0.07
     Leisure
    -0.06
    udget
    -0.06
    abel
    -0.06
    otherapy
    -0.06
     è«
    -0.06
    ÙĪاع
    -0.06
    .eql
    -0.06
    POSITIVE LOGITS
     breathing
    0.15
     food
    0.12
     breathe
    0.12
     breath
    0.11
     oxygen
    0.11
    food
    0.10
     FOOD
    0.10
    -food
    0.10
     respir
    0.10
     breathable
    0.10
    Activations Density 0.067%

    No Known Activations