© 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. 81621
    Prev
    Next
    INDEX
    Explanations

    references to legal terminology and proceedings

    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
    angl
    -0.07
    ç«Ļ
    -0.07
     zad
    -0.06
    ihat
    -0.06
    .TestTools
    -0.06
     Uncomment
    -0.06
    ascar
    -0.06
    rant
    -0.06
     surveys
    -0.06
     CONTRIBUTORS
    -0.06
    POSITIVE LOGITS
     facts
    0.12
     Facts
    0.10
    facts
    0.09
     factual
    0.09
    events
    0.07
    /events
    0.07
     undis
    0.07
     events
    0.07
     uncont
    0.07
     glean
    0.07
    Activations Density 0.035%

    No Known Activations