© 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. 15-LLAMASCOPE-RES-131K
    11. 86887
    Prev
    Next
    INDEX
    Explanations

    references to obligations, permissions, and actions related to requests and authorizations

    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
     however
    -0.07
     lay
    -0.06
    engl
    -0.06
     hint
    -0.06
     other
    -0.06
     verg
    -0.06
     However
    -0.06
     kolej
    -0.06
    eyse
    -0.05
    /or
    -0.05
    POSITIVE LOGITS
     ÙħØ«ÙĦا
    0.09
    	TokenName
    0.08
    Äı
    0.08
    inki
    0.08
    ISIBLE
    0.08
     ÃĸrneÄŁin
    0.07
    kü
    0.07
     напÑĢимеÑĢ
    0.07
     напÑĢиклад
    0.07
    :UITableView
    0.07
    Activations Density 0.068%

    No Known Activations