© 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. 58306
    Prev
    Next
    INDEX
    Explanations

    elements related to customization and features in design

    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
    retty
    -0.09
    hea
    -0.08
     اختÙĦ
    -0.07
    uky
    -0.07
    olon
    -0.07
    ãĤį
    -0.07
    zdy
    -0.07
    arith
    -0.07
    ebra
    -0.07
    à¸ģระ
    -0.07
    POSITIVE LOGITS
    ábado
    0.07
     Preis
    0.07
    ácil
    0.06
     Vital
    0.06
    ipeg
    0.06
    ÛĮÙĨÙĩ
    0.06
     Hoff
    0.06
     joint
    0.06
    ials
    0.06
     Excell
    0.06
    Activations Density 0.001%

    No Known Activations