© 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. 75497
    Prev
    Next
    INDEX
    Explanations

    numerical values or measurements

    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
    a
    -0.07
    анÑĤи
    -0.06
     fitte
    -0.05
    iol
    -0.05
    ospace
    -0.05
    contest
    -0.05
    adu
    -0.05
    ugar
    -0.05
     Gust
    -0.05
    (
    -0.05
    POSITIVE LOGITS
    licer
    0.08
    üssen
    0.08
    ispens
    0.07
    alm
    0.07
    uesta
    0.07
    iliz
    0.07
    ysqli
    0.07
    trys
    0.07
    loff
    0.07
    oggler
    0.07
    Activations Density 0.000%

    No Known Activations