© 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. 89759
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations

    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
     Stern
    -0.07
     chalk
    -0.07
    uros
    -0.07
     lag
    -0.06
    ultipart
    -0.06
    ovit
    -0.06
     Ordered
    -0.06
    olute
    -0.06
     asympt
    -0.06
    abaj
    -0.06
    POSITIVE LOGITS
    баÑĩ
    0.07
     Quý
    0.06
     existence
    0.06
     Mort
    0.06
     Boundary
    0.06
    .xhtml
    0.06
    .exist
    0.06
    ¶
    0.06
    ÙĪÙĦÙĩ
    0.06
     sát
    0.06
    Activations Density 0.500%

    No Known Activations