© 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. 4119
    Prev
    Next
    INDEX
    Explanations

    details about patio umbrellas and their characteristics

    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
    amic
    -0.06
    è¨
    -0.06
     setting
    -0.06
    onda
    -0.06
    CompatActivity
    -0.06
    rve
    -0.05
    activo
    -0.05
     macro
    -0.05
    endi
    -0.05
    iku
    -0.05
    POSITIVE LOGITS
     designs
    0.09
    款
    0.08
     Designs
    0.08
     styles
    0.08
    953
    0.07
    ifix
    0.07
     colors
    0.07
     Variation
    0.06
    styles
    0.06
     sizes
    0.06
    Activations Density 0.009%

    No Known Activations