© 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. 74587
    Prev
    Next
    INDEX
    Explanations

    references to market trends and economic forecasts

    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
    //{{
    -0.07
    ekli
    -0.07
     Tomorrow
    -0.06
     Platt
    -0.06
     ?>"/>↵
    -0.06
    anca
    -0.06
    /slick
    -0.06
    ëŀĮ
    -0.06
    TEAM
    -0.06
    .MixedReality
    -0.06
    POSITIVE LOGITS
    uz
    0.06
     Sem
    0.06
    uze
    0.06
     singly
    0.06
    Segments
    0.06
    anny
    0.05
    actly
    0.05
     Antony
    0.05
     infer
    0.05
    Ý
    0.05
    Activations Density 0.001%

    No Known Activations