© 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 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. 118830
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to sales and market performance across various sectors

    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
    éŁ¿
    -0.06
    eur
    -0.06
    reff
    -0.06
    udies
    -0.05
     sounding
    -0.05
     promin
    -0.05
     tên
    -0.05
    _CM
    -0.05
     ranging
    -0.05
     when
    -0.05
    POSITIVE LOGITS
     total
    0.09
     gross
    0.08
    goog
    0.08
     baÅŁÄ±na
    0.08
    हन
    0.07
     overall
    0.07
    DataContext
    0.07
     Gross
    0.07
    acho
    0.07
     Pek
    0.07
    Activations Density 0.062%

    No Known Activations