© 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. 29574
    Prev
    Next
    INDEX
    Explanations

    file extensions or types related to computer code and images

    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
    ez
    -0.07
    norm
    -0.07
    eut
    -0.07
    core
    -0.07
     Prospect
    -0.07
    òi
    -0.06
    ÑĩÑĥ
    -0.06
    friend
    -0.06
    balance
    -0.06
     sous
    -0.06
    POSITIVE LOGITS
    .datab
    0.07
    äge
    0.06
     forState
    0.06
    leen
    0.06
     nhiên
    0.06
    Streamer
    0.06
     upper
    0.06
     Tos
    0.06
    raç
    0.05
    ÏĦÏģ
    0.05
    Activations Density 0.001%

    No Known Activations