© 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. 15-LLAMASCOPE-RES-131K
    11. 26628
    Prev
    Next
    INDEX
    Explanations

    the word "So" used prominently at the beginning of sentences

    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
    quo
    -0.07
    shaw
    -0.07
    aucoup
    -0.07
    inded
    -0.07
    ocha
    -0.07
    .gg
    -0.07
    vinc
    -0.06
     Kendrick
    -0.06
    uper
    -0.06
    quam
    -0.06
    POSITIVE LOGITS
    å¹ķ
    0.07
    aken
    0.07
    isci
    0.06
     finally
    0.06
    iele
    0.06
    atura
    0.06
    isto
    0.06
     Stanton
    0.06
    ften
    0.06
    fern
    0.06
    Activations Density 0.013%

    No Known Activations