© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 118779
    Prev
    Next
    INDEX
    Explanations

    instances of the word "know" and its variations, indicating knowledge or awareness

    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
    ç·Ĵ
    -0.06
    932
    -0.06
    обов
    -0.06
     Found
    -0.06
    oundary
    -0.06
    aub
    -0.06
    anto
    -0.06
     Boulevard
    -0.06
     Benef
    -0.06
     Formal
    -0.06
    POSITIVE LOGITS
     enough
    0.07
     how
    0.07
     unb
    0.07
    POSITORY
    0.07
    hist
    0.07
    .bz
    0.06
    rer
    0.06
     background
    0.06
     bur
    0.06
    ac
    0.06
    Activations Density 0.022%

    No Known Activations