© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 69023
    Prev
    Next
    INDEX
    Explanations

    numerical references related to dates and periods in history

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ValueCollection
    -0.07
    ickest
    -0.07
    exampleInput
    -0.06
    ices
    -0.06
    -www
    -0.06
    anst
    -0.06
    /*č↵
    -0.06
    illow
    -0.06
    anco
    -0.06
    ække
    -0.06
    POSITIVE LOGITS
    igli
    0.06
    RIES
    0.06
    Period
    0.06
    /qt
    0.06
    quit
    0.06
    dyn
    0.06
    ãĥ¼ãĥľ
    0.06
     Period
    0.06
     period
    0.06
    Late
    0.06
    Activations Density 0.004%

    No Known Activations