© 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. 17-LLAMASCOPE-RES-131K
    11. 86914
    Prev
    Next
    INDEX
    Explanations

    phrases relating to waiting or delays in time

    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
    ziel
    -0.06
    olet
    -0.06
     spend
    -0.06
    ä»ĺ
    -0.06
     Spend
    -0.06
     spends
    -0.06
     spending
    -0.06
     fairy
    -0.06
    eded
    -0.05
    eler
    -0.05
    POSITIVE LOGITS
    771
    0.07
    ä½
    0.07
     mesel
    0.07
    760
    0.07
    Ãłng
    0.07
    кид
    0.07
    createClass
    0.07
    CAF
    0.07
    OfDay
    0.07
    Mathf
    0.07
    Activations Density 0.009%

    No Known Activations