© 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. 121530
    Prev
    Next
    INDEX
    Explanations

    the word "while" and its variations in various forms and 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
    elia
    -0.07
     liter
    -0.06
    isu
    -0.06
    oret
    -0.06
    iaz
    -0.06
    ika
    -0.06
    $rs
    -0.06
    ys
    -0.05
    adel
    -0.05
    hall
    -0.05
    POSITIVE LOGITS
     also
    0.08
    ĵåIJį
    0.07
     simultaneously
    0.07
    efore
    0.07
     Also
    0.07
    ãĤĪãģ³
    0.07
     ALSO
    0.06
    ãĤ
    0.06
    rette
    0.06
    Also
    0.06
    Activations Density 0.016%

    No Known Activations