© 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. 116554
    Prev
    Next
    INDEX
    Explanations

    instances of emotional or impactful expressions, particularly transitions and changes

    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
     subur
    -0.06
     plu
    -0.05
     Lange
    -0.05
     forth
    -0.05
     altern
    -0.05
     config
    -0.05
    icorn
    -0.05
    H
    -0.05
    set
    -0.05
    /format
    -0.05
    POSITIVE LOGITS
    okino
    0.08
    ÌĨ
    0.08
    æĭ©
    0.08
    ä¸įäºĨ
    0.07
    бÑĥдÑĮ
    0.07
    theless
    0.07
    bject
    0.07
    .scalablytyped
    0.07
    ASCADE
    0.07
    criptor
    0.07
    Activations Density 0.105%

    No Known Activations