© 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. 17-LLAMASCOPE-RES-131K
    11. 60523
    Prev
    Next
    INDEX
    Explanations

    terms related to the functionality and application of tools or devices

    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
    pitch
    -0.06
     NSLocalizedString
    -0.06
    aphore
    -0.06
    angs
    -0.06
    avia
    -0.06
    æĸ
    -0.06
    elper
    -0.06
     ÑĥÑģÑĤ
    -0.06
    amik
    -0.06
     Andres
    -0.06
    POSITIVE LOGITS
     withd
    0.07
    imde
    0.07
    ter
    0.07
     anywhere
    0.07
     anytime
    0.07
    ifold
    0.07
    ForObject
    0.06
    à¹Īวมà¸ģ
    0.06
     Nass
    0.06
    adnÃŃ
    0.06
    Activations Density 0.015%

    No Known Activations