© 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. 1480
    Prev
    Next
    INDEX
    Explanations

    references to specific artists and songs in the music industry

    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
     Geile
    -0.08
     münchen
    -0.08
     Äijá»į
    -0.08
    rý
    -0.08
    ymm
    -0.08
    etheless
    -0.07
    readcr
    -0.07
    >NN
    -0.07
    çĽijåIJ¬é¡µéĿ¢
    -0.07
     Cumhur
    -0.07
    POSITIVE LOGITS
    â
    0.06
    ador
    0.06
     Fram
    0.06
     Ever
    0.05
     aged
    0.05
     â
    0.05
     Late
    0.05
    âĢij
    0.05
     Dev
    0.05
     Modified
    0.05
    Activations Density 0.011%

    No Known Activations