© 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. 9-LLAMASCOPE-RES-131K
    11. 96243
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with financial figures or transactions

    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
    editable
    -0.07
     Belt
    -0.06
    ìĤ°
    -0.06
    ıyoruz
    -0.06
    ijken
    -0.06
    trl
    -0.06
     slippery
    -0.06
    azines
    -0.06
    اÙħÙĦ
    -0.06
    .wall
    -0.06
    POSITIVE LOGITS
    877
    0.07
    akis
    0.07
    osi
    0.06
    arius
    0.06
    atch
    0.06
     Ä°st
    0.06
    ella
    0.06
     WithEvents
    0.06
     SUBSTITUTE
    0.06
    isz
    0.06
    Activations Density 0.028%

    No Known Activations