© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56539
    Prev
    Next
    INDEX
    Explanations

    descriptions of features and advantages of an invention

    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
    ł
    -0.07
    ternet
    -0.07
    pii
    -0.07
    .nanoTime
    -0.07
    ocks
    -0.07
    iddi
    -0.06
    izon
    -0.06
    orris
    -0.06
    rahim
    -0.06
    erken
    -0.06
    POSITIVE LOGITS
     stru
    0.07
     CHARSET
    0.07
     Bog
    0.07
     cum
    0.06
     {*
    0.06
     kum
    0.06
     ÄĮer
    0.06
    isclosed
    0.06
     inventive
    0.06
    iles
    0.06
    Activations Density 0.071%

    No Known Activations