© 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. 70725
    Prev
    Next
    INDEX
    Explanations

    mentions of days of the week, particularly in a calendar context

    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
    rote
    -0.07
     Gala
    -0.06
    TC
    -0.06
    ÑĥÑĩа
    -0.06
     tá»Ļc
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    vanished
    -0.06
    ted
    -0.06
     Tonight
    -0.06
     tonight
    -0.06
    POSITIVE LOGITS
    oppel
    0.08
    /month
    0.07
    оÑĤÑĢеб
    0.06
    ths
    0.06
    ìĶ©
    0.06
    оÑĢд
    0.06
    öz
    0.06
    alc
    0.06
    ltra
    0.06
    issent
    0.06
    Activations Density 0.004%

    No Known Activations