© 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. 103473
    Prev
    Next
    INDEX
    Explanations

    references to music and artistic expression

    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
    aise
    -0.08
    nerg
    -0.07
    ALLE
    -0.07
     Wor
    -0.06
    zen
    -0.06
    ãĤį
    -0.06
    APH
    -0.06
    olland
    -0.06
     backpage
    -0.06
    LOAT
    -0.06
    POSITIVE LOGITS
     odds
    0.07
     stuff
    0.07
     mostly
    0.07
    orex
    0.07
    mostly
    0.07
    ritz
    0.06
    ]|[
    0.06
     unanimous
    0.06
    822
    0.06
    oucher
    0.06
    Activations Density 0.027%

    No Known Activations