© 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. 83611
    Prev
    Next
    INDEX
    Explanations

    terms related to nutrition and health impacts of food

    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
    å¥ij
    -0.07
    ayout
    -0.07
     avantaj
    -0.06
    erde
    -0.06
    iedy
    -0.06
    ê·¼
    -0.06
    undler
    -0.06
    lique
    -0.06
    393
    -0.06
    .heroku
    -0.06
    POSITIVE LOGITS
     cholesterol
    0.08
    -ra
    0.07
     LDL
    0.07
    olesterol
    0.07
     Leisure
    0.06
     intake
    0.06
    çĥ
    0.06
    ç¡
    0.06
     saturated
    0.06
     Nurses
    0.06
    Activations Density 0.004%

    No Known Activations