© 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. 42102
    Prev
    Next
    INDEX
    Explanations

    features and qualities of products, particularly their durability and environmental impact

    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
    ainment
    -0.07
    ëĦ
    -0.07
    tainment
    -0.06
    amp
    -0.06
    hal
    -0.06
    ì¡°
    -0.06
    serter
    -0.06
    EMPTY
    -0.06
    amma
    -0.06
    leta
    -0.06
    POSITIVE LOGITS
     durability
    0.11
     durable
    0.09
    IRT
    0.09
     Dur
    0.08
    dur
    0.08
    Dur
    0.08
     longevity
    0.08
     lasting
    0.08
     dur
    0.08
     bá»ģn
    0.08
    Activations Density 0.015%

    No Known Activations