© 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. 119283
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to standards and excellence across various contexts

    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
     dikke
    -0.07
    WithValue
    -0.07
    uggy
    -0.07
     Autof
    -0.07
    .infinity
    -0.07
    tron
    -0.06
     змÑĸ
    -0.06
     Solic
    -0.06
    ewan
    -0.06
    åī²
    -0.06
    POSITIVE LOGITS
     standards
    0.10
     quality
    0.08
     Standards
    0.08
     levels
    0.07
    -quality
    0.07
    quality
    0.07
    pitch
    0.07
    hift
    0.07
     liv
    0.07
     setters
    0.06
    Activations Density 0.014%

    No Known Activations