© 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. 93757
    Prev
    Next
    INDEX
    Explanations

    temporal references and events related to specific dates and times

    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
     minim
    -0.06
    åī
    -0.06
    ãĥ¼ãĥ
    -0.06
     Tay
    -0.05
     Historic
    -0.05
    inez
    -0.05
    ermann
    -0.05
    íĥĪ
    -0.05
     Zhu
    -0.05
    once
    -0.05
    POSITIVE LOGITS
     ÑģÑĥÑĤ
    0.08
    .Utc
    0.07
    jet
    0.07
    åĩĮ
    0.07
     wake
    0.07
    ToDevice
    0.07
    Wake
    0.07
    esome
    0.07
    ipel
    0.07
     wakes
    0.07
    Activations Density 0.007%

    No Known Activations