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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72997
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation for individuals and experiences

    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
    ieux
    -0.07
    enga
    -0.07
    ingle
    -0.07
     infra
    -0.07
     relief
    -0.06
    été
    -0.06
    rops
    -0.06
    urgence
    -0.06
    zet
    -0.06
    ccione
    -0.06
    POSITIVE LOGITS
     acquaintance
    0.07
     existence
    0.07
     exist
    0.07
     such
    0.07
     exists
    0.06
     ì¡
    0.06
     Jas
    0.06
    å±ŀäºİ
    0.06
     ÏĦÏĮÏĥο
    0.06
    asty
    0.06
    Activations Density 0.017%

    No Known Activations