© 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. 95142
    Prev
    Next
    INDEX
    Explanations

    descriptions of weather and environmental changes

    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
    presso
    -0.07
     ActionTypes
    -0.07
    cmds
    -0.07
    oding
    -0.07
    arking
    -0.07
    oreal
    -0.06
     \/
    -0.06
    .dump
    -0.06
    ConnectionFactory
    -0.06
    .Inner
    -0.06
    POSITIVE LOGITS
     wind
    0.13
    wind
    0.12
     gust
    0.10
    Wind
    0.10
     winds
    0.10
     Wind
    0.09
     blowing
    0.09
    .wind
    0.08
    åIJ¹
    0.08
     Winds
    0.08
    Activations Density 0.022%

    No Known Activations