© 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. 9-LLAMASCOPE-RES-131K
    11. 95045
    Prev
    Next
    INDEX
    Explanations

    terms related to synthetic fabrics and materials

    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
    lessly
    -0.06
    aceutical
    -0.06
    arah
    -0.06
    awy
    -0.06
     down
    -0.06
     compelling
    -0.06
     Seth
    -0.06
    fra
    -0.06
    abouts
    -0.06
    ÃŁ
    -0.06
    POSITIVE LOGITS
     sint
    0.07
    Äįer
    0.07
    ntax
    0.07
    itas
    0.07
    áž
    0.07
    жно
    0.07
    اÙĦØ¥
    0.07
     nackte
    0.07
    áºŃt
    0.07
     Verfügung
    0.07
    Activations Density 0.002%

    No Known Activations