© 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. 119841
    Prev
    Next
    INDEX
    Explanations

    numerical references and significant dates

    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
     Corrections
    -0.06
    ear
    -0.06
    deer
    -0.05
     zer
    -0.05
    dma
    -0.05
    raison
    -0.05
    koa
    -0.05
     Haut
    -0.05
    ng
    -0.05
     Hayden
    -0.05
    POSITIVE LOGITS
     number
    0.10
     ÑĩиÑģло
    0.10
     ÑĩиÑģла
    0.10
    numer
    0.09
    -num
    0.09
    zahl
    0.09
    -number
    0.09
    numero
    0.09
    number
    0.09
     ÑĩиÑģ
    0.09
    Activations Density 0.015%

    No Known Activations