© 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. 26914
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to congratulations and praise

    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
    Anchor
    -0.07
    mailer
    -0.07
    iem
    -0.07
    seed
    -0.07
    azor
    -0.07
     詳細
    -0.07
    iets
    -0.07
    ÑĪев
    -0.07
    .AF
    -0.07
    룬
    -0.06
    POSITIVE LOGITS
    ation
    0.08
    ationToken
    0.07
    antly
    0.07
     congrat
    0.07
     congratulate
    0.07
    emplate
    0.06
    ion
    0.06
    -worthy
    0.06
    atory
    0.06
    lation
    0.06
    Activations Density 0.004%

    No Known Activations