© 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. 79374
    Prev
    Next
    INDEX
    Explanations

    references to caring, effort, and various forms of work

    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
     complete
    -0.07
     slightly
    -0.06
    beck
    -0.06
    _COMPLETE
    -0.06
    soever
    -0.06
    _complete
    -0.06
     Complete
    -0.06
    ensis
    -0.06
     slight
    -0.06
     universally
    -0.06
    POSITIVE LOGITS
    LOTS
    0.10
    ubat
    0.07
     lately
    0.07
    lots
    0.07
    otal
    0.07
    ãİ
    0.07
    /cms
    0.07
     disag
    0.07
    ramework
    0.07
     Lot
    0.07
    Activations Density 0.087%

    No Known Activations