© 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. 27383
    Prev
    Next
    INDEX
    Explanations

    concepts related to reflection and reflective surfaces

    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
    _simps
    -0.07
    ighter
    -0.07
    arkin
    -0.07
    chestra
    -0.07
     realiza
    -0.07
    гл
    -0.06
    uyá»ĩn
    -0.06
    ÐŁÐļ
    -0.06
    ourg
    -0.06
    ÙĪص
    -0.06
    POSITIVE LOGITS
    /ref
    0.10
     reflection
    0.09
    reflection
    0.09
    Reflection
    0.09
     Reflection
    0.09
    reflect
    0.08
     reflections
    0.08
     reflect
    0.07
     Reflect
    0.07
     bounced
    0.07
    Activations Density 0.017%

    No Known Activations