© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5726
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to database structures and functions

    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
    illus
    -0.07
    絶
    -0.07
    ifr
    -0.07
     Sec
    -0.06
     zel
    -0.06
    enek
    -0.06
     hab
    -0.06
     cot
    -0.06
    è¾¼
    -0.06
     Legion
    -0.06
    POSITIVE LOGITS
     ÑĢазм
    0.07
    agma
    0.07
    oggle
    0.06
     Zahl
    0.06
    unger
    0.06
    ÅĻÃŃ
    0.06
    essler
    0.06
    arella
    0.06
    lsen
    0.06
    à¸Ĭà¸Ļ
    0.06
    Activations Density 0.044%

    No Known Activations