© 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. 60106
    Prev
    Next
    INDEX
    Explanations

    references to pricing and affordability in products or services

    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
    gere
    -0.07
    วร
    -0.06
    práv
    -0.06
    æ¡IJ
    -0.06
    inem
    -0.06
     kå
    -0.06
    γον
    -0.06
    ick
    -0.06
    enne
    -0.06
    appen
    -0.06
    POSITIVE LOGITS
     competitive
    0.10
     competit
    0.09
     pricing
    0.09
     charges
    0.08
    compet
    0.08
     prices
    0.08
    competitive
    0.07
     competitiveness
    0.07
     compét
    0.07
    Compet
    0.07
    Activations Density 0.019%

    No Known Activations