© 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. 81752
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to construction and infrastructure improvement projects

    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
    afs
    -0.06
     spot
    -0.06
     Stuff
    -0.06
    à¸Ńะ
    -0.06
    rrha
    -0.06
    .bundle
    -0.06
    å¥Ĺ
    -0.06
     flex
    -0.06
     asiat
    -0.06
    itele
    -0.06
    POSITIVE LOGITS
     villagers
    0.09
     village
    0.08
    egin
    0.07
     community
    0.07
     installation
    0.06
    ÑīÑĸ
    0.06
    bourg
    0.06
     رÙĪستا
    0.06
    inator
    0.06
     Community
    0.06
    Activations Density 0.020%

    No Known Activations