© 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. 82353
    Prev
    Next
    INDEX
    Explanations

    technical terms related to materials science and sample fabrication

    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
    kube
    -0.07
    ullet
    -0.06
    ppt
    -0.06
     Entry
    -0.06
    annon
    -0.06
     radians
    -0.06
     oss
    -0.06
    aeper
    -0.06
    ÑĢÑĥÑĤ
    -0.06
     æij
    -0.06
    POSITIVE LOGITS
    defs
    0.07
    ãĥĭãĥ¼
    0.07
     Wells
    0.07
     Dün
    0.07
     Alv
    0.07
    ıklı
    0.07
     Merk
    0.06
    ixels
    0.06
    blo
    0.06
    ç¿Ķ
    0.06
    Activations Density 0.006%

    No Known Activations