© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82170
    Prev
    Next
    INDEX
    Explanations

    references to celestial events and conditions, particularly relating to the Moon

    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
    agine
    -0.06
    enga
    -0.06
    achu
    -0.06
     McGill
    -0.06
     unilateral
    -0.06
    寿
    -0.06
    Bird
    -0.06
    Gain
    -0.05
    uel
    -0.05
    Rain
    -0.05
    POSITIVE LOGITS
     moon
    0.24
    moon
    0.20
     Moon
    0.19
     lunar
    0.17
    Moon
    0.17
     moons
    0.15
     Lunar
    0.12
    æľĪ
    0.10
     Full
    0.10
     æľĪ
    0.10
    Activations Density 0.034%

    No Known Activations