© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72098
    Prev
    Next
    INDEX
    Explanations

    economic terms related to publishing and music industry transactions

    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
    ìļ´
    -0.07
    oppins
    -0.06
     suit
    -0.06
    éģĭ
    -0.06
     Ferd
    -0.06
    _CPP
    -0.06
    lite
    -0.06
     Progressive
    -0.06
    preview
    -0.05
    nout
    -0.05
    POSITIVE LOGITS
     sales
    0.09
    sales
    0.08
    Ñģол
    0.07
     Sales
    0.07
    åĶ®
    0.07
    ëıĮ
    0.07
    porte
    0.07
    Sales
    0.07
    éĶĢåĶ®
    0.07
    bach
    0.07
    Activations Density 0.004%

    No Known Activations