© 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. 127257
    Prev
    Next
    INDEX
    Explanations

    keywords related to seeking information or updates about people or events

    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
    ilip
    -0.08
    ValueChanged
    -0.06
    uela
    -0.06
     إذ
    -0.06
    ÅĽci
    -0.06
    byn
    -0.06
    kbd
    -0.06
     hari
    -0.06
    og
    -0.06
    _representation
    -0.06
    POSITIVE LOGITS
    iddles
    0.07
     Ø´ÙĪ
    0.06
    edException
    0.06
     dash
    0.06
    بÙĪر
    0.06
    isches
    0.06
    Įĵ
    0.06
     плиÑĤ
    0.06
    สà¸ĩ
    0.06
     Mond
    0.06
    Activations Density 0.002%

    No Known Activations