© 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. 104454
    Prev
    Next
    INDEX
    Explanations

    numerical representations of dates, particularly related to September 11 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
     ble
    -0.06
    ortal
    -0.06
     Kim
    -0.06
     gì
    -0.06
    531
    -0.06
    race
    -0.06
     z
    -0.06
     d
    -0.06
    arehouse
    -0.06
     Ble
    -0.06
    POSITIVE LOGITS
    omi
    0.08
    terior
    0.07
    filer
    0.07
    tober
    0.07
    çĿĽ
    0.07
     ë´ī
    0.07
    kker
    0.07
     nhỼ
    0.06
    iego
    0.06
    份
    0.06
    Activations Density 0.002%

    No Known Activations