© 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. 62635
    Prev
    Next
    INDEX
    Explanations

    instances of time or frequency-related language

    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
    odb
    -0.08
    riad
    -0.07
    ki
    -0.07
    jist
    -0.07
    agon
    -0.07
    pong
    -0.07
    eter
    -0.07
    маз
    -0.07
    urette
    -0.07
     ki
    -0.07
    POSITIVE LOGITS
    omanip
    0.06
    vik
    0.06
    .mozilla
    0.06
    ilden
    0.06
     Gund
    0.06
    ayo
    0.06
    aha
    0.05
    nem
    0.05
    494
    0.05
     Marketplace
    0.05
    Activations Density 0.000%

    No Known Activations