© 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. 119329
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal arguments and definitions

    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
     vig
    -0.07
     viz
    -0.06
     Brunswick
    -0.06
    DataTable
    -0.06
    986
    -0.05
    ennie
    -0.05
    unga
    -0.05
     adj
    -0.05
     worldwide
    -0.05
     respective
    -0.05
    POSITIVE LOGITS
    esModule
    0.07
    andaÅŁ
    0.07
    prene
    0.07
    ÅĪ
    0.07
     Král
    0.07
    Manifest
    0.07
     UINavigationController
    0.07
    Ø
    0.07
    _Report
    0.07
     Qaeda
    0.07
    Activations Density 0.001%

    No Known Activations