© 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. 107048
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal milestones and significant life events

    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
     decades
    -0.07
     generations
    -0.06
    代
    -0.06
    apur
    -0.06
    854
    -0.06
    oles
    -0.06
     Generation
    -0.06
     generation
    -0.05
     Iss
    -0.05
    arat
    -0.05
    POSITIVE LOGITS
    ilon
    0.08
     vůbec
    0.07
     últimos
    0.07
     Orientation
    0.07
    çģ°
    0.06
     âĨIJ
    0.06
    oload
    0.06
    ãģ°ãģĭãĤĬ
    0.06
    ÑĢок
    0.06
     last
    0.06
    Activations Density 0.032%

    No Known Activations