© 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. 60249
    Prev
    Next
    INDEX
    Explanations

    expressions of commitment to customer relationships and quality service

    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
    ever
    -0.07
    weet
    -0.06
    423
    -0.06
    ver
    -0.06
    ayment
    -0.06
    ville
    -0.06
     Fleet
    -0.06
    venge
    -0.06
    othermal
    -0.06
    722
    -0.06
    POSITIVE LOGITS
    jed
    0.08
    installer
    0.07
    éĽª
    0.07
     slic
    0.07
    .Hit
    0.07
    ukt
    0.07
     ank
    0.07
    jad
    0.06
    огод
    0.06
    deen
    0.06
    Activations Density 0.031%

    No Known Activations