© 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. 30691
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions indicating relationships and actions in sentences

    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
    uta
    -0.07
    ANJI
    -0.07
     misc
    -0.07
     Erd
    -0.07
    /↵↵↵↵
    -0.07
     Fal
    -0.06
    -hooks
    -0.06
    ffen
    -0.06
    ispens
    -0.06
    ittel
    -0.06
    POSITIVE LOGITS
    /browse
    0.07
    ("<?
    0.07
    ivist
    0.06
     Incontri
    0.06
    -es
    0.06
    ãģ¹ãģį
    0.06
    yen
    0.06
    frica
    0.06
    aster
    0.06
    .Bean
    0.06
    Activations Density 0.021%

    No Known Activations