© 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. 72135
    Prev
    Next
    INDEX
    Explanations

    references to buildings or sites related to public or industrial infrastructure

    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
    ãĥªãĤ«
    -0.06
     eros
    -0.06
     range
    -0.06
    inea
    -0.06
    lal
    -0.06
     preced
    -0.06
    ogg
    -0.06
     мой
    -0.06
    ì§Ī
    -0.05
    atif
    -0.05
    POSITIVE LOGITS
    -turned
    0.14
     Converted
    0.09
    converted
    0.09
    -now
    0.09
    è·¡
    0.08
    turned
    0.08
    Converted
    0.08
     converted
    0.08
     تبدÛĮÙĦ
    0.08
    nbsp
    0.08
    Activations Density 0.024%

    No Known Activations