© 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. 59365
    Prev
    Next
    INDEX
    Explanations

    descriptions of daily routines and personal reflections

    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
     Nights
    -0.10
     nights
    -0.09
     evenings
    -0.08
     sunset
    -0.08
     dusk
    -0.08
    å¤ķ
    -0.07
     soir
    -0.07
     tonight
    -0.07
    auer
    -0.07
    itty
    -0.07
    POSITIVE LOGITS
     breakfast
    0.18
     morning
    0.16
     Breakfast
    0.16
     Morning
    0.13
    Morning
    0.13
     mornings
    0.12
     early
    0.12
     ìķĦ침
    0.11
     Early
    0.10
    Early
    0.10
    Activations Density 0.061%

    No Known Activations