© 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. 17-LLAMASCOPE-RES-131K
    11. 86215
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Daily" and variations of its usage

    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
    ads
    -0.07
    梨
    -0.07
    Ãłu
    -0.07
    ÑĢез
    -0.06
    кид
    -0.06
    weis
    -0.06
    pecified
    -0.06
    setDisplay
    -0.06
    алÑĥ
    -0.06
    年度
    -0.06
    POSITIVE LOGITS
     Daily
    0.09
    Daily
    0.07
     daily
    0.07
    daily
    0.07
    orsi
    0.07
    yg
    0.07
    ead
    0.07
    lr
    0.06
    ihil
    0.06
    gw
    0.06
    Activations Density 0.009%

    No Known Activations