© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94311
    Prev
    Next
    INDEX
    Explanations

    elements related to lively celebrations and dancing

    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
    AndView
    -0.08
    .scalablytyped
    -0.08
    usal
    -0.07
    lug
    -0.07
    antity
    -0.07
    ogh
    -0.07
    \<^
    -0.07
    ertino
    -0.07
    uden
    -0.07
    åĬĩ
    -0.07
    POSITIVE LOGITS
     dance
    0.18
     dancing
    0.17
     Dance
    0.15
    dance
    0.15
     danced
    0.14
     dances
    0.14
     Dancing
    0.14
     dancers
    0.13
     dancer
    0.13
    èĪŀ
    0.10
    Activations Density 0.284%

    No Known Activations