© 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. 73607
    Prev
    Next
    INDEX
    Explanations

    numerical values or quantities

    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
    aida
    -0.07
     kern
    -0.07
     strugg
    -0.06
    OA
    -0.06
    iflower
    -0.06
    kea
    -0.06
    anta
    -0.06
    orgia
    -0.06
     Craigslist
    -0.06
    侯
    -0.06
    POSITIVE LOGITS
    hub
    0.07
    θÏħ
    0.07
     Gerry
    0.07
    leck
    0.07
     Yates
    0.06
    kich
    0.06
    umes
    0.06
    ottes
    0.06
    Hub
    0.06
    isan
    0.06
    Activations Density 0.002%

    No Known Activations