© 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. 85123
    Prev
    Next
    INDEX
    Explanations

    concepts related to ocean and climate change metrics

    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
    ihn
    -0.07
     recreate
    -0.07
    ();)
    -0.06
     native
    -0.06
    ohn
    -0.06
     densities
    -0.06
     Walt
    -0.06
    atron
    -0.06
    udas
    -0.06
     Rosenstein
    -0.06
    POSITIVE LOGITS
     decade
    0.07
    pearance
    0.07
     offsetY
    0.06
     offsetX
    0.06
    ouro
    0.06
    erli
    0.06
    olini
    0.06
    IOD
    0.06
    owi
    0.06
     Temp
    0.06
    Activations Density 0.002%

    No Known Activations