© 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. 15-LLAMASCOPE-RES-131K
    11. 88670
    Prev
    Next
    INDEX
    Explanations

    references to the "Lorem Ipsum" placeholder text commonly used in graphic design and publishing

    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
    cel
    -0.07
    iez
    -0.07
    ictionary
    -0.07
     skl
    -0.07
    OrDefault
    -0.07
    igon
    -0.07
    anie
    -0.07
    voucher
    -0.07
    erval
    -0.06
    duino
    -0.06
    POSITIVE LOGITS
    uchs
    0.06
    -transitional
    0.06
    verity
    0.06
    ommen
    0.06
     Kemp
    0.06
    \Foundation
    0.06
    ologna
    0.06
    aren
    0.06
    /assert
    0.06
    ushima
    0.06
    Activations Density 0.001%

    No Known Activations