© 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. 56766
    Prev
    Next
    INDEX
    Explanations

    botanical and taxonomical terminology

    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
    ungle
    -0.07
     доÑģ
    -0.07
     Gum
    -0.06
    _pet
    -0.06
     Santa
    -0.06
     trader
    -0.06
    Yaw
    -0.06
    477
    -0.06
     Trader
    -0.06
     Pacific
    -0.06
    POSITIVE LOGITS
     Directive
    0.07
     UEFA
    0.07
     Ves
    0.07
     Euro
    0.07
     European
    0.06
     european
    0.06
    arkan
    0.06
    quette
    0.06
     Europe
    0.06
     euro
    0.06
    Activations Density 0.010%

    No Known Activations