© 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. 15-LLAMASCOPE-RES-131K
    11. 86513
    Prev
    Next
    INDEX
    Explanations

    expressions and concepts related to grace and mercy

    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
    IODevice
    -0.06
    orno
    -0.06
    NASDAQ
    -0.06
    thing
    -0.06
    -force
    -0.06
     sincer
    -0.06
    antis
    -0.06
    à¥ģन
    -0.05
    edata
    -0.05
    423
    -0.05
    POSITIVE LOGITS
    нимаеÑĤ
    0.08
    obus
    0.08
     Wand
    0.07
    нимаÑĤÑĮ
    0.07
    лиÑĪком
    0.07
    .Xaml
    0.07
     SpoleÄį
    0.07
    amd
    0.07
    atte
    0.07
     Frid
    0.07
    Activations Density 0.058%

    No Known Activations