© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30067
    Prev
    Next
    INDEX
    Explanations

    expressions related to gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    iek
    -0.06
    ardo
    -0.06
    agas
    -0.06
     Buckley
    -0.06
     zd
    -0.06
     Ziel
    -0.06
    ouncill
    -0.06
    kus
    -0.06
     Indian
    -0.06
     discre
    -0.06
    POSITIVE LOGITS
    odash
    0.07
    -б
    0.07
    beit
    0.07
    æ¢
    0.07
    iola
    0.07
    inspace
    0.07
    irit
    0.07
    ANNER
    0.07
    utral
    0.06
    Ñģом
    0.06
    Activations Density 0.001%

    No Known Activations