© 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. 2417
    Prev
    Next
    INDEX
    Explanations

    references to street food in Bangkok

    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
    umper
    -0.07
    SPA
    -0.07
     UPC
    -0.07
    ertino
    -0.06
    ihad
    -0.06
    åºĵ
    -0.06
    à¹Ģà¸ĺ
    -0.06
    ибли
    -0.06
     library
    -0.06
    ATERIAL
    -0.06
    POSITIVE LOGITS
     street
    0.10
    æij
    0.10
     vendor
    0.09
    vendors
    0.09
     vendors
    0.09
     Street
    0.08
    Street
    0.08
    street
    0.08
    /vendors
    0.08
     STREET
    0.08
    Activations Density 0.007%

    No Known Activations