© 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. 74443
    Prev
    Next
    INDEX
    Explanations

    references to programming tools or environments

    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
    vere
    -0.08
    žit
    -0.07
    losion
    -0.07
    лиÑĤ
    -0.07
    unge
    -0.06
     Aires
    -0.06
    .translation
    -0.06
     QApplication
    -0.06
    باÙĨ
    -0.06
     opr
    -0.06
    POSITIVE LOGITS
    agrid
    0.06
    RD
    0.06
    ¼
    0.06
     Schmidt
    0.06
    aben
    0.06
    illon
    0.06
     Baum
    0.06
    amax
    0.06
    ugi
    0.06
    ÑĢÑĸд
    0.06
    Activations Density 0.000%

    No Known Activations