© 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. 60933
    Prev
    Next
    INDEX
    Explanations

    instances of cancellations or postponements related to events

    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
     aba
    -0.06
    thon
    -0.06
     intr
    -0.06
    æĪ²
    -0.06
    ongs
    -0.06
    .tags
    -0.06
    ifty
    -0.06
    ugu
    -0.06
    nbr
    -0.06
     searching
    -0.05
    POSITIVE LOGITS
     пеÑĢен
    0.07
    esel
    0.07
    TestCategory
    0.07
    æ¼Ķ
    0.07
    Sold
    0.06
    AREST
    0.06
     SOLD
    0.06
    sold
    0.06
     cancellation
    0.06
     performances
    0.06
    Activations Density 0.011%

    No Known Activations