© 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 EvalsExportsinterp-engineNEWAPI 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. 1846
    Prev
    Next
    INDEX
    Explanations

    descriptions of daily activities and experiences in a narrative style

    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
    -0.09
     nights
    -0.09
    auer
    -0.08
    reesome
    -0.08
    marvin
    -0.07
     evenings
    -0.06
    ibble
    -0.06
    wa
    -0.06
     Compatible
    -0.06
    ekten
    -0.06
    POSITIVE LOGITS
     morning
    0.12
     breakfast
    0.11
     today
    0.10
    today
    0.09
     again
    0.09
     Breakfast
    0.09
     Morning
    0.09
     Today
    0.09
    Today
    0.08
     TODAY
    0.08
    Activations Density 0.049%

    No Known Activations