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

    Neuronpedia

    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. 61401
    Prev
    Next
    INDEX
    Explanations

    references to legislative committees and processes

    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
    ny
    -0.06
    mal
    -0.06
     privacy
    -0.06
    anke
    -0.06
     AuthenticationService
    -0.06
    sworth
    -0.06
     confronting
    -0.06
    ascript
    -0.05
    alli
    -0.05
     Privacy
    -0.05
    POSITIVE LOGITS
    ovaly
    0.08
    auce
    0.07
    ovna
    0.07
     promot
    0.07
    ovÃŃ
    0.07
    oplay
    0.07
    uced
    0.07
    ãĥĥãĥĦ
    0.07
    âl
    0.07
    499
    0.06
    Activations Density 0.004%

    No Known Activations