© 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. 17-LLAMASCOPE-RES-131K
    11. 85049
    Prev
    Next
    INDEX
    Explanations

    the word "best" in various contexts

    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
    üçük
    -0.08
    gression
    -0.06
    caled
    -0.06
    ned
    -0.06
    antu
    -0.06
    ÙĪدÛĮ
    -0.06
    deen
    -0.06
    ations
    -0.06
     indeb
    -0.06
     fewer
    -0.06
    POSITIVE LOGITS
    seller
    0.13
    owing
    0.12
    -selling
    0.12
    -known
    0.10
    ow
    0.10
    -case
    0.10
    ows
    0.09
    ial
    0.09
    ower
    0.09
    SELL
    0.09
    Activations Density 0.047%

    No Known Activations