© 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. 1394
    Prev
    Next
    INDEX
    Explanations

    temporal and date-related references in the context of incidents

    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
    umont
    -0.07
    icious
    -0.06
    assen
    -0.06
     hypothesis
    -0.06
    apo
    -0.06
    otec
    -0.06
     Ax
    -0.06
     applied
    -0.06
    antity
    -0.06
    енз
    -0.06
    POSITIVE LOGITS
     Ihr
    0.07
    çijŁ
    0.06
    enet
    0.06
    ³
    0.06
    typeid
    0.06
    ाà¤ĩल
    0.06
     Seal
    0.06
    isor
    0.06
    ยà¸Ńà¸Ķ
    0.06
     Kiss
    0.06
    Activations Density 0.002%

    No Known Activations