© 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. 107513
    Prev
    Next
    INDEX
    Explanations

    specific instructions and requirements regarding software or plugin specifications

    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
    è¼Ŀ
    -0.06
    HEMA
    -0.06
    anou
    -0.06
    ãĥŃãĥ¼
    -0.06
    439
    -0.06
     اÙĦرÙħزÙĬØ©
    -0.06
     Retro
    -0.06
    Blueprint
    -0.06
    ICO
    -0.06
    лада
    -0.06
    POSITIVE LOGITS
     its
    0.07
     hotel
    0.06
    oola
    0.06
    MMM
    0.06
     eventual
    0.06
    ä¹ĥ
    0.06
    edin
    0.06
     UIControl
    0.06
    User
    0.06
     shar
    0.06
    Activations Density 0.075%

    No Known Activations