© 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. 106590
    Prev
    Next
    INDEX
    Explanations

    references to the word "Staples" and related forms, indicating an emphasis on the brand or object associated with it

    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
    herits
    -0.07
    indow
    -0.07
    ãĥ¼ãĥ³
    -0.06
    kening
    -0.06
    postcode
    -0.06
    amics
    -0.06
    rams
    -0.06
    ernel
    -0.06
    antro
    -0.06
    ousing
    -0.06
    POSITIVE LOGITS
    fel
    0.08
    ylim
    0.08
    yl
    0.07
    orz
    0.07
    ]={↵
    0.07
    olis
    0.07
    leton
    0.07
    ford
    0.07
    éĽ²
    0.06
    fish
    0.06
    Activations Density 0.003%

    No Known Activations