© 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 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. 106531
    Prev
    Next
    INDEX
    Explanations

    emotions related to satisfaction or contentment

    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
     and
    -0.07
     ever
    -0.07
     only
    -0.07
    .
    -0.06
     somehow
    -0.06
    ,
    -0.06
     beautiful
    -0.06
     no
    -0.06
     far
    -0.06
     absolutely
    -0.06
    POSITIVE LOGITS
    overall
    0.09
    ojis
    0.08
     fairly
    0.08
     decent
    0.08
    alet
    0.08
    artz
    0.08
    âĢĮÙħ
    0.07
    usters
    0.07
    ivec
    0.07
     considering
    0.07
    Activations Density 0.071%

    No Known Activations