© 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. 94589
    Prev
    Next
    INDEX
    Explanations

    information related to mills and their historical significance

    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
    ropol
    -0.06
    vida
    -0.06
    ÑĢÑĸд
    -0.06
    ucha
    -0.06
    ammo
    -0.06
     veri
    -0.06
    adium
    -0.06
    aza
    -0.06
    budget
    -0.06
    +xml
    -0.06
    POSITIVE LOGITS
     mills
    0.08
     mill
    0.08
     powered
    0.07
     Classifier
    0.07
     id
    0.07
     Classification
    0.07
     flour
    0.06
    ë°Ģ
    0.06
     Machines
    0.06
    powered
    0.06
    Activations Density 0.007%

    No Known Activations