© 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. 15-LLAMASCOPE-RES-131K
    11. 87978
    Prev
    Next
    INDEX
    Explanations

    references to food and dining experiences

    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
    zik
    -0.07
    otec
    -0.06
    lehem
    -0.06
     деÑĢжавноÑĹ
    -0.06
    пи
    -0.06
     Regional
    -0.06
    nem
    -0.06
    crest
    -0.06
    DN
    -0.06
     Vern
    -0.06
    POSITIVE LOGITS
     English
    0.14
    English
    0.14
     USA
    0.13
     American
    0.13
     Western
    0.13
     western
    0.13
     foreigners
    0.13
    USA
    0.12
     Americans
    0.12
    english
    0.12
    Activations Density 0.447%

    No Known Activations