© 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. 38442
    Prev
    Next
    INDEX
    Explanations

    expressions of well-wishes and congratulations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Expressions of well-wishes, congratulations, and formal acknowledgments of achievements, often ending with positive affirmations about the recipient.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered by @lu-christina
    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
     éĩij
    -0.07
    Ñĩина
    -0.06
    каÑĢ
    -0.06
    иком
    -0.06
    .Dev
    -0.06
    esser
    -0.06
    Gener
    -0.06
    estruction
    -0.05
    asz
    -0.05
     TRI
    -0.05
    POSITIVE LOGITS
     Congratulations
    0.13
     congratulations
    0.13
    Congratulations
    0.13
     congr
    0.12
     Cong
    0.10
    Cong
    0.10
     thank
    0.09
    ç¥Ŀ
    0.08
     congratulate
    0.08
     cong
    0.08
    Activations Density 0.219%

    No Known Activations