© 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. 125270
    Prev
    Next
    INDEX
    Explanations

    references to ownership and company-related terminology

    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
    tuk
    -0.08
    .synthetic
    -0.07
    Adj
    -0.07
     Stout
    -0.07
    gard
    -0.06
    vä
    -0.06
    ä¼ij
    -0.06
    cia
    -0.06
    adia
    -0.06
     ÙĬØ´
    -0.06
    POSITIVE LOGITS
    DataExchange
    0.07
    æ¢
    0.07
     controller
    0.06
     privacy
    0.06
    -controller
    0.06
    à¸Ļาย
    0.06
    å¾ģ
    0.06
    yles
    0.06
     kne
    0.06
     controllers
    0.06
    Activations Density 0.001%

    No Known Activations