© 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. 78926
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dance" and its variations, indicating a focus on themes of dancing and movement

    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
    .scalablytyped
    -0.09
    ossal
    -0.08
    icari
    -0.08
     kå
    -0.08
    grunt
    -0.08
    eyse
    -0.07
    hlas
    -0.07
    icaret
    -0.07
    ilet
    -0.07
    osg
    -0.07
    POSITIVE LOGITS
    with
    0.06
     around
    0.06
     dance
    0.06
     danced
    0.06
     sor
    0.06
    wei
    0.06
     Alle
    0.06
     with
    0.06
     flames
    0.05
     slim
    0.05
    Activations Density 0.011%

    No Known Activations