© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 83196
    Prev
    Next
    INDEX
    Explanations

    references to works of art or architecture

    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
    conut
    -0.08
    arious
    -0.08
    quette
    -0.08
    atos
    -0.08
    storybook
    -0.08
     æĬķ稿
    -0.07
    isol
    -0.07
    criptor
    -0.07
    rap
    -0.07
    .getState
    -0.07
    POSITIVE LOGITS
    bench
    0.08
     art
    0.07
     ward
    0.06
     nature
    0.06
    ben
    0.06
     fiction
    0.06
    (s
    0.06
    artin
    0.06
    piece
    0.05
    class
    0.05
    Activations Density 0.007%

    No Known Activations