© 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. 5126
    Prev
    Next
    INDEX
    Explanations

    concepts related to regulations and technical 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
    incinn
    -0.07
    оÑĢож
    -0.06
    GPU
    -0.06
     moi
    -0.06
    ApplicationBuilder
    -0.06
    izr
    -0.06
    ãĥIJãĥ¼
    -0.06
     Denis
    -0.06
     bearings
    -0.06
    -plugins
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĥĢ
    0.07
     виÑĤ
    0.07
    Race
    0.07
     Distance
    0.07
    Propagation
    0.06
    Chi
    0.06
     Terminal
    0.06
    ureen
    0.06
     terminals
    0.06
    eln
    0.06
    Activations Density 0.004%

    No Known Activations