© 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. 88821
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or emphasize the significance of time and conditions

    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
     Tul
    -0.07
    ML
    -0.06
     no
    -0.06
    824
    -0.06
     resto
    -0.06
    kara
    -0.06
     (
    -0.06
    ingers
    -0.06
    æĽ²
    -0.06
     Klo
    -0.06
    POSITIVE LOGITS
     nunca
    0.08
    never
    0.08
     unprecedented
    0.08
     никогда
    0.08
     ever
    0.07
     jamais
    0.07
    ever
    0.07
     назад
    0.07
    Never
    0.07
    رÙĪع
    0.07
    Activations Density 0.064%

    No Known Activations