© 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. 59571
    Prev
    Next
    INDEX
    Explanations

    inquiries about well-being and health

    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
    xec
    -0.07
     Specification
    -0.07
    pcodes
    -0.07
    posable
    -0.07
    ltra
    -0.07
     specification
    -0.06
    blr
    -0.06
    chema
    -0.06
    æ®
    -0.06
    ализи
    -0.06
    POSITIVE LOGITS
     performances
    0.07
     vit
    0.07
    ych
    0.06
    illac
    0.06
    ئت
    0.06
    delay
    0.06
     overall
    0.06
    ion
    0.06
    vit
    0.06
     fares
    0.06
    Activations Density 0.008%

    No Known Activations