© 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. 94338
    Prev
    Next
    INDEX
    Explanations

    dates and years 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
     Merr
    -0.07
     mech
    -0.06
    odÃŃ
    -0.06
     ÑģÑĤÑĢа
    -0.06
    ستÙĩ
    -0.06
    zman
    -0.06
     reports
    -0.06
     Kı
    -0.06
     sworn
    -0.06
     Heb
    -0.06
    POSITIVE LOGITS
    ToLocal
    0.07
    avel
    0.07
    cape
    0.06
    tiler
    0.06
    ä¸įå¾Ĺ
    0.06
     upcoming
    0.06
    ramework
    0.06
    DEX
    0.06
    adata
    0.06
    BoxLayout
    0.06
    Activations Density 0.018%

    No Known Activations