© 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. 363
    Prev
    Next
    INDEX
    Explanations

    expressions related to quantities

    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
    pear
    -0.07
    izu
    -0.07
    sworth
    -0.07
    ather
    -0.07
    ITTE
    -0.07
    uien
    -0.07
    ÑģоÑĤ
    -0.07
    /front
    -0.06
    amed
    -0.06
    under
    -0.06
    POSITIVE LOGITS
    inous
    0.09
    esseract
    0.09
    vise
    0.08
    ois
    0.08
    naire
    0.07
    naires
    0.07
    gua
    0.07
    taire
    0.07
    alist
    0.07
    -wise
    0.07
    Activations Density 0.008%

    No Known Activations