© 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. 107276
    Prev
    Next
    INDEX
    Explanations

    instances of the word "while" indicating concurrent actions

    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
    aises
    -0.08
    ILT
    -0.07
    ibel
    -0.07
    hof
    -0.07
    gren
    -0.07
    .manage
    -0.07
    šov
    -0.07
    ntl
    -0.07
    trl
    -0.07
    abox
    -0.07
    POSITIVE LOGITS
    à¥ĩà¤
    0.06
    ea
    0.06
    while
    0.06
    While
    0.06
    lli
    0.06
     hanging
    0.06
     enjoy
    0.06
    .ast
    0.06
     while
    0.05
     enjoying
    0.05
    Activations Density 0.013%

    No Known Activations