© 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 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. 89239
    Prev
    Next
    INDEX
    Explanations

    mentions of artists and their contributions in various fields

    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
    enti
    -0.08
     Leader
    -0.07
    _ASCII
    -0.07
    Leader
    -0.06
    łéĻ¤
    -0.06
     Collaboration
    -0.06
    enko
    -0.06
     Pc
    -0.06
     pÅĻiÄįemž
    -0.06
    oux
    -0.06
    POSITIVE LOGITS
     magazine
    0.07
     another
    0.07
     radio
    0.07
    another
    0.07
     newsletter
    0.07
     media
    0.07
     editorial
    0.06
    :host
    0.06
     marketing
    0.06
     music
    0.06
    Activations Density 0.061%

    No Known Activations