© 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. 87941
    Prev
    Next
    INDEX
    Explanations

    elements related to art, creativity, and community engagement

    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
     ìŀĪê³ł
    -0.09
     ìŀĪëĬĶëį°
    -0.09
    ãģĬãĤĬ
    -0.08
     zwar
    -0.08
    [a
    -0.08
     yaparak
    -0.08
    ãģ¨ãģªãĤĬ
    -0.08
    ìĿ´ê³ł
    -0.07
     sice
    -0.07
    ãģ°ãģĭãĤĬ
    -0.07
    POSITIVE LOGITS
    .↵
    0.11
    ).↵
    0.11
    ).
    0.10
    .č↵
    0.10
    âĢ¦
    0.09
    ãĢĤ↵
    0.08
    .
    0.08
    isha
    0.08
    ."↵
    0.08
    âĢ¦âĢ¦
    0.08
    Activations Density 5.904%

    No Known Activations