© 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 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. 3526
    Prev
    Next
    INDEX
    Explanations

    temporal references and expressions related to 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
    hest
    -0.08
    TimeStamp
    -0.07
    ets
    -0.06
    ERRU
    -0.06
     date
    -0.06
    weg
    -0.06
    terra
    -0.06
     territorial
    -0.06
    ãĤ¹ãĥĪ
    -0.06
    etu
    -0.06
    POSITIVE LOGITS
     spent
    0.10
    ulo
    0.08
    iversit
    0.08
    spent
    0.08
    úi
    0.08
    ofday
    0.07
    ously
    0.07
    OfDay
    0.07
    =time
    0.07
    ÃŃrk
    0.07
    Activations Density 0.033%

    No Known Activations