© 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. 93487
    Prev
    Next
    INDEX
    Explanations

    various grammatical articles and prepositions in Italian

    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
     unf
    -0.07
    ----------------------------------------------------------------------------
    -0.07
    onis
    -0.06
    EVER
    -0.06
    cheid
    -0.06
     Unidos
    -0.06
    .paginator
    -0.06
     пÑĢиÑħод
    -0.06
     Gins
    -0.06
     trú
    -0.06
    POSITIVE LOGITS
    placeholders
    0.08
     âĹĦ
    0.07
    loff
    0.07
    uru
    0.06
    .yang
    0.06
    æĦı
    0.06
    ¦æĥħ
    0.06
    GenerationStrategy
    0.05
     Automobile
    0.05
    anner
    0.05
    Activations Density 0.024%

    No Known Activations