© 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. 26869
    Prev
    Next
    INDEX
    Explanations

    phrases related to congratulatory messages and awards

    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
    елеÑĦ
    -0.08
    retorno
    -0.08
    ĶåĽŀ
    -0.07
    Å¡ky
    -0.07
    (æĹ¥
    -0.07
     плаÑģÑĤи
    -0.07
    ÐĬ
    -0.07
    edores
    -0.07
    Assignable
    -0.07
    ONO
    -0.07
    POSITIVE LOGITS
     our
    0.09
     all
    0.08
     teams
    0.08
     winner
    0.08
    0.07
     upon
    0.07
     recent
    0.07
     winners
    0.07
     team
    0.06
     newly
    0.06
    Activations Density 0.010%

    No Known Activations