© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127783
    Prev
    Next
    INDEX
    Explanations

    references to suppliers and their popularity in Asia

    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
    oman
    -0.08
    essler
    -0.06
    ierge
    -0.06
    uds
    -0.06
    onde
    -0.06
    fee
    -0.06
    ible
    -0.06
    rez
    -0.06
    ummer
    -0.05
    æ¬
    -0.05
    POSITIVE LOGITS
     ÙħÙĨØ·
    0.06
     Jed
    0.06
    jed
    0.06
     Vulcan
    0.06
    ãĥ¼ãĥľ
    0.06
     Nas
    0.06
     quadratic
    0.06
    è¹
    0.06
    ENTA
    0.06
    orno
    0.06
    Activations Density 0.002%

    No Known Activations