© 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. 18669
    Prev
    Next
    INDEX
    Explanations

    numerical values related to years or dates

    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
    alink
    -0.07
    asha
    -0.07
    fed
    -0.07
    adow
    -0.06
    ample
    -0.06
    //}}
    -0.06
    caffold
    -0.06
    rust
    -0.06
    avenous
    -0.06
    acha
    -0.06
    POSITIVE LOGITS
    .EventQueue
    0.07
    راد
    0.06
    384
    0.06
     Ders
    0.06
    647
    0.06
    edl
    0.06
    .RadioButton
    0.06
     iken
    0.06
    .GridView
    0.05
    ahan
    0.05
    Activations Density 0.001%

    No Known Activations