© 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. 127151
    Prev
    Next
    INDEX
    Explanations

    words that suggest specific locations or geographic features

    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
    aname
    -0.06
     jag
    -0.06
    organic
    -0.06
    dialogs
    -0.06
     toto
    -0.06
     governors
    -0.06
    Bubble
    -0.06
    acob
    -0.06
     govern
    -0.06
    LOB
    -0.06
    POSITIVE LOGITS
    -bordered
    0.10
    leaf
    0.10
     Grove
    0.09
    dale
    0.09
    -tree
    0.08
    -lined
    0.08
    chwitz
    0.08
    iele
    0.08
    -haired
    0.08
    -colored
    0.08
    Activations Density 0.047%

    No Known Activations