© 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. 107043
    Prev
    Next
    INDEX
    Explanations

    instances of monetary values or financial terms

    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
    اÙĨÙĪ
    -0.09
    ãĥ¼ãĥª
    -0.08
    keit
    -0.07
    IDEO
    -0.07
    Ñĩа
    -0.07
    Ïħκ
    -0.07
    اÙĨ
    -0.07
    yg
    -0.07
    bac
    -0.07
    ertino
    -0.07
    POSITIVE LOGITS
    onto
    0.07
    itten
    0.07
    ieber
    0.07
    etter
    0.06
    illy
    0.06
    s
    0.06
    uli
    0.06
    iu
    0.06
     mandate
    0.06
    oen
    0.06
    Activations Density 0.017%

    No Known Activations