© 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. 3300
    Prev
    Next
    INDEX
    Explanations

    references to UNESCO World Heritage Sites and their recognition

    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
    rowsing
    -0.07
    eck
    -0.06
    /release
    -0.06
    .createStatement
    -0.06
    __":↵
    -0.06
    onor
    -0.06
    ÑĤов
    -0.06
    @student
    -0.05
     Armed
    -0.05
     simplex
    -0.05
    POSITIVE LOGITS
     UNESCO
    0.12
    UN
    0.08
     bullet
    0.08
    oney
    0.07
    .UN
    0.07
    alic
    0.07
    rial
    0.07
    LAR
    0.07
    Sites
    0.07
    BUFF
    0.07
    Activations Density 0.005%

    No Known Activations