© 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. 90896
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate keeping pace or maintaining progress with various aspects of life or systems

    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
    eware
    -0.08
    upon
    -0.06
    ³
    -0.06
    ekil
    -0.06
    fter
    -0.06
    .StoredProcedure
    -0.06
    ANNEL
    -0.06
    avenport
    -0.06
    anka
    -0.06
    erguson
    -0.06
    POSITIVE LOGITS
     rabbit
    0.07
     reality
    0.07
    AndGet
    0.07
     stride
    0.07
    TEGER
    0.07
     demands
    0.06
    IsNull
    0.06
     requirements
    0.06
     rabbits
    0.06
     Requirements
    0.06
    Activations Density 0.008%

    No Known Activations