© 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. 15-LLAMASCOPE-RES-131K
    11. 87399
    Prev
    Next
    INDEX
    Explanations

    key terms related to research and academic work

    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
    ilia
    -0.07
    èŃ·
    -0.07
    asti
    -0.06
    รà¸ĩ
    -0.06
     Radi
    -0.06
    .TestTools
    -0.06
    jac
    -0.06
    åIJ¹
    -0.06
    enna
    -0.06
     radi
    -0.06
    POSITIVE LOGITS
    hoot
    0.08
    dle
    0.07
    æļ
    0.07
     DependencyProperty
    0.07
     ÙħÛĮÙĦادÛĮ
    0.06
    lint
    0.06
    indre
    0.06
    aybe
    0.06
    quired
    0.06
    ivery
    0.06
    Activations Density 0.025%

    No Known Activations