© 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 EvalsExportsinterp-engineNEWAPI 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. 27268
    Prev
    Next
    INDEX
    Explanations

    mentions of the holiday season and related 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
    opis
    -0.08
    CTYPE
    -0.07
    ibold
    -0.07
    acemark
    -0.07
    å·ŀ
    -0.07
     derec
    -0.07
    orem
    -0.07
    .openConnection
    -0.07
    older
    -0.07
    aspect
    -0.07
    POSITIVE LOGITS
     past
    0.08
     years
    0.07
     field
    0.07
    0.07
     daily
    0.07
     archives
    0.06
     months
    0.06
     canon
    0.06
     time
    0.06
    ug
    0.06
    Activations Density 0.031%

    No Known Activations