© 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. 127895
    Prev
    Next
    INDEX
    Explanations

    variations of the word "une" and language-related terms indicating unease

    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
    tein
    -0.07
    achu
    -0.07
    guard
    -0.07
    ucing
    -0.07
    olly
    -0.07
    wick
    -0.06
    /MPL
    -0.06
    elsius
    -0.06
    ewise
    -0.06
    κÏħ
    -0.06
    POSITIVE LOGITS
    ptune
    0.07
    clipse
    0.07
     Laden
    0.07
    ogue
    0.06
    oop
    0.06
    ogui
    0.06
    up
    0.06
    ices
    0.06
    ither
    0.06
    prs
    0.06
    Activations Density 0.008%

    No Known Activations