© 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. 79476
    Prev
    Next
    INDEX
    Explanations

    phrases related to consistency and tradition in accomplishments and efforts

    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
    /-
    -0.07
    Completed
    -0.07
    ãģķãģ¾
    -0.06
    haus
    -0.06
    reed
    -0.06
    rames
    -0.06
     selber
    -0.06
    tol
    -0.06
    279
    -0.06
    tal
    -0.06
    POSITIVE LOGITS
     trend
    0.10
    ä¸ĭåİ»
    0.10
     momentum
    0.10
     tradition
    0.09
     traditions
    0.08
     Tradition
    0.07
     interrupted
    0.07
     continues
    0.07
     trends
    0.07
     streak
    0.07
    Activations Density 0.040%

    No Known Activations