© 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. 74324
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and business decisions

    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
    agna
    -0.08
    adolu
    -0.07
    gars
    -0.07
    eah
    -0.07
    quin
    -0.07
    lew
    -0.07
    ç±
    -0.07
    bose
    -0.06
    zioni
    -0.06
    viar
    -0.06
    POSITIVE LOGITS
     deal
    0.07
     instantly
    0.06
     immediately
    0.06
     cann
    0.06
    æĥ
    0.06
     immediate
    0.06
     product
    0.06
    nik
    0.06
    ŀ
    0.05
    lon
    0.05
    Activations Density 0.017%

    No Known Activations