© 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. 89591
    Prev
    Next
    INDEX
    Explanations

    phrases quantifying large amounts or significance

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    inan
    -0.07
     ÐłÐ°
    -0.07
    ansi
    -0.07
    -Speed
    -0.06
    å¹
    -0.06
     hữu
    -0.06
    æŁ³
    -0.06
     execut
    -0.06
    åĮ
    -0.06
    426
    -0.06
    POSITIVE LOGITS
     opportunity
    0.07
    wash
    0.07
    ries
    0.06
     time
    0.06
     MetroFramework
    0.06
    ÙħØ©
    0.06
    emas
    0.06
     enough
    0.06
     number
    0.06
     bite
    0.06
    Activations Density 0.008%

    No Known Activations