© 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. 59051
    Prev
    Next
    INDEX
    Explanations

    occurrences of dates and times in the text

    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
    .sam
    -0.08
    ,eg
    -0.08
    ekil
    -0.08
    bject
    -0.08
    _dy
    -0.07
     оÑĤли
    -0.07
    loff
    -0.07
    виÑĩ
    -0.07
    .va
    -0.07
     ZákladnÃŃ
    -0.07
    POSITIVE LOGITS
     December
    0.08
     March
    0.08
     May
    0.07
     February
    0.07
     January
    0.07
     June
    0.06
     November
    0.06
     July
    0.06
     Mar
    0.06
    acle
    0.06
    Activations Density 0.154%

    No Known Activations