© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 90605
    Prev
    Next
    INDEX
    Explanations

    references to Microsoft Surface devices and related products

    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
    è£ı
    -0.07
     Amateur
    -0.07
    andom
    -0.07
    ANDOM
    -0.07
    ennie
    -0.06
    AsyncResult
    -0.06
    asiswa
    -0.06
    annes
    -0.06
     Decoration
    -0.06
    arda
    -0.06
    POSITIVE LOGITS
     models
    0.07
    é¦Ļ
    0.06
    -*-
    0.06
    .utf
    0.06
    le
    0.06
     Ñģклад
    0.06
     locally
    0.06
     con
    0.06
    ëł¥ìĿ´
    0.06
    eld
    0.06
    Activations Density 0.001%

    No Known Activations