© 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. 89592
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and structures

    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
    buz
    -0.08
    (encoding
    -0.07
    inclu
    -0.07
     æĬķ稿
    -0.07
    ẻ
    -0.07
    ensely
    -0.07
     tslib
    -0.06
     Sır
    -0.06
    iliation
    -0.06
    _REQUIRE
    -0.06
    POSITIVE LOGITS
    lab
    0.06
     INCIDENTAL
    0.06
    icionar
    0.06
     Bail
    0.06
    ammad
    0.06
    alculate
    0.06
    ahoma
    0.06
    //@
    0.06
    itz
    0.06
     Nev
    0.06
    Activations Density 0.035%

    No Known Activations