© 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. 127565
    Prev
    Next
    INDEX
    Explanations

    financial and investment-related terms and concepts

    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
    oire
    -0.09
     DÄĽ
    -0.07
     *__
    -0.07
    æ´ŀ
    -0.07
    raki
    -0.07
     ladder
    -0.07
    été
    -0.07
     Hüs
    -0.07
    اÙħÛĮÙĨ
    -0.06
    ниÑĤ
    -0.06
    POSITIVE LOGITS
     nor
    0.12
     any
    0.11
    ä»»ä½ķ
    0.10
     particular
    0.09
     anybody
    0.08
     ANY
    0.08
     anyone
    0.08
     or
    0.08
     Nor
    0.07
    -any
    0.07
    Activations Density 0.012%

    No Known Activations