© 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. 83878
    Prev
    Next
    INDEX
    Explanations

    references to music and musical elements

    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
     lately
    -0.07
    ãĤ¾
    -0.07
    VERRIDE
    -0.06
    lobs
    -0.06
    .BLL
    -0.06
    tright
    -0.06
     newest
    -0.06
     Westbrook
    -0.06
     th
    -0.06
     shar
    -0.06
    POSITIVE LOGITS
    UIFont
    0.06
    idding
    0.06
    út
    0.06
    idis
    0.06
    aram
    0.06
     seminal
    0.06
    angel
    0.06
     Peer
    0.06
     later
    0.06
    qui
    0.06
    Activations Density 0.000%

    No Known Activations