© 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. 2790
    Prev
    Next
    INDEX
    Explanations

    references to servitude and commitment to 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
    ods
    -0.07
    reds
    -0.06
    575
    -0.06
    phem
    -0.06
    hti
    -0.06
    139
    -0.06
    nock
    -0.06
    aste
    -0.06
    pell
    -0.06
    -exc
    -0.06
    POSITIVE LOGITS
    abus
    0.07
    θη
    0.07
     chir
    0.07
    æŁ´
    0.07
    Ïģη
    0.06
    ccione
    0.06
     MOS
    0.06
     Backbone
    0.06
    isman
    0.06
    .GO
    0.06
    Activations Density 0.001%

    No Known Activations