© 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. 60545
    Prev
    Next
    INDEX
    Explanations

    various sizes and dimensions, particularly related to clothing and measurements

    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
     thumbs
    -0.06
    ignon
    -0.06
    ander
    -0.06
    oner
    -0.06
    owan
    -0.06
     Ashe
    -0.06
    afen
    -0.05
     ups
    -0.05
    imple
    -0.05
    nak
    -0.05
    POSITIVE LOGITS
     beyond
    0.09
     Beyond
    0.08
    ople
    0.08
    Beyond
    0.08
     trá»Ŀi
    0.07
    LEGRO
    0.07
    ÄĻż
    0.07
    amax
    0.07
     extreme
    0.07
    unta
    0.07
    Activations Density 0.031%

    No Known Activations