© 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. 15-LLAMASCOPE-RES-131K
    11. 1432
    Prev
    Next
    INDEX
    Explanations

    phrases related to aesthetic appreciation and home improvement

    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
    Ä±ÅŁÄ±k
    -0.07
    brit
    -0.06
    incinn
    -0.06
    umsuz
    -0.06
    лиз
    -0.06
    giene
    -0.06
     yoksa
    -0.06
    .px
    -0.06
    inyin
    -0.06
     Independent
    -0.06
    POSITIVE LOGITS
     transform
    0.09
     finished
    0.08
     project
    0.08
     transforms
    0.08
    Transform
    0.07
     transformations
    0.07
     transformation
    0.07
     transformed
    0.07
     Transform
    0.07
    project
    0.07
    Activations Density 0.054%

    No Known Activations