© 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. 27045
    Prev
    Next
    INDEX
    Explanations

    transitional words and phrases indicating contrast or conjunctions

    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
    Prov
    -0.08
    //{{
    -0.08
    æĵ
    -0.08
     Hakk
    -0.07
    ëŀ«
    -0.06
    ··
    -0.06
    ÏĦα
    -0.06
    mainwindow
    -0.06
     Prov
    -0.06
     возÑĢаÑģÑĤа
    -0.06
    POSITIVE LOGITS
    $MESS
    0.06
    utherford
    0.06
     Article
    0.06
    prech
    0.05
    anus
    0.05
     graduated
    0.05
     Somerset
    0.05
     longer
    0.05
     assist
    0.05
     MPH
    0.05
    Activations Density 0.001%

    No Known Activations