© 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. 73646
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that represent structured information, particularly related to dates and episodes in a series

    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
     fine
    -0.06
     few
    -0.06
     Lep
    -0.06
     Ale
    -0.05
    u
    -0.05
    ¬
    -0.05
     Dam
    -0.05
    ÂŃ
    -0.05
     fe
    -0.05
    272
    -0.05
    POSITIVE LOGITS
    #ad
    0.09
     addCriterion
    0.09
    dit
    0.08
    ,LOCATION
    0.08
    Intialized
    0.07
    addtogroup
    0.07
    vro
    0.07
    ettel
    0.07
    enco
    0.07
    lfw
    0.07
    Activations Density 0.003%

    No Known Activations