© 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. 123655
    Prev
    Next
    INDEX
    Explanations

    references to holidays and festive seasons

    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
    iaz
    -0.07
    chw
    -0.07
     Fior
    -0.06
     recent
    -0.06
     earlier
    -0.06
    ted
    -0.06
    uesta
    -0.06
     paralle
    -0.06
     Zuk
    -0.06
     recently
    -0.06
    POSITIVE LOGITS
    GMEM
    0.08
    ãģ£ãģ
    0.07
    adoo
    0.07
    952
    0.07
    outu
    0.07
     nackt
    0.07
    FindObject
    0.07
    aux
    0.07
    .Tween
    0.06
     пеÑĢек
    0.06
    Activations Density 0.016%

    No Known Activations