© 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. 60107
    Prev
    Next
    INDEX
    Explanations

    references to UNESCO World Heritage Sites

    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
     Horizon
    -0.07
    eroon
    -0.06
     Terrain
    -0.06
    oro
    -0.06
    溪
    -0.06
    emark
    -0.06
    eck
    -0.06
    xxxxxxxx
    -0.06
     Reyes
    -0.05
    ff
    -0.05
    POSITIVE LOGITS
    .Clock
    0.08
     status
    0.08
    ngr
    0.07
    CATEGORY
    0.07
    eru
    0.07
    æļ
    0.07
    گرÛĮ
    0.07
    átka
    0.07
    Ļ
    0.07
    -worthy
    0.07
    Activations Density 0.002%

    No Known Activations