© 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. 108930
    Prev
    Next
    INDEX
    Explanations

    the presence of the substring "Tr" across various contexts

    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
    ertas
    -0.07
    ilded
    -0.07
    clid
    -0.07
    ensis
    -0.07
    pliers
    -0.07
    385
    -0.06
    theid
    -0.06
    engers
    -0.06
    erview
    -0.06
    uppy
    -0.06
    POSITIVE LOGITS
    uman
    0.07
    uc
    0.07
    ö
    0.07
     Tr
    0.06
    immel
    0.06
    asti
    0.06
    akt
    0.06
    .Safe
    0.06
    .Tasks
    0.06
     Hardy
    0.06
    Activations Density 0.027%

    No Known Activations