© 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. 119987
    Prev
    Next
    INDEX
    Explanations

    references to a financial analysis or stock market discussion

    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
     feder
    -0.06
    fed
    -0.06
     Lobby
    -0.06
    äch
    -0.06
     lobby
    -0.06
     trunk
    -0.06
    lobby
    -0.06
    lob
    -0.06
    mey
    -0.05
     Ink
    -0.05
    POSITIVE LOGITS
     Fool
    0.09
     stocks
    0.08
     dividend
    0.07
    antom
    0.07
    arel
    0.07
    theses
    0.06
    aller
    0.06
     avg
    0.06
    tsx
    0.06
     Analyst
    0.06
    Activations Density 0.007%

    No Known Activations