© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15593
    Prev
    Next
    INDEX
    Explanations

    conjunctions and comparative phrases related to financial statistics

    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
    FullYear
    -0.07
     Jacqu
    -0.07
    entin
    -0.07
    icro
    -0.06
    ewis
    -0.06
    PÅĻÃŃ
    -0.06
    arat
    -0.06
    ersiz
    -0.06
     SHR
    -0.06
     Hatch
    -0.06
    POSITIVE LOGITS
    ehen
    0.07
     others
    0.07
    oyal
    0.06
    usto
    0.06
    ukan
    0.06
    iesz
    0.06
    tok
    0.06
     Iron
    0.06
    eyer
    0.06
    357
    0.06
    Activations Density 0.002%

    No Known Activations