© 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. 104994
    Prev
    Next
    INDEX
    Explanations

    meteorological terms and weather-related descriptions

    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
    agal
    -0.07
    oeff
    -0.07
    mür
    -0.07
    _atts
    -0.07
     Nová
    -0.07
    MEA
    -0.07
     Weiner
    -0.07
    ł
    -0.07
    ÙĬÙĦÙĬ
    -0.06
    lasses
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĤ¿
    0.07
    etik
    0.07
     Sabha
    0.07
     deflate
    0.06
    _HPP
    0.06
     FS
    0.06
     astronomical
    0.06
    etsk
    0.06
    stown
    0.06
    \Migrations
    0.05
    Activations Density 0.010%

    No Known Activations