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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 70925
    Prev
    Next
    INDEX
    Explanations

    terms related to increases or raises in prices and funding

    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
    Ùģر
    -0.06
    -fw
    -0.06
    urred
    -0.06
    rine
    -0.06
     progress
    -0.06
     wound
    -0.05
     descent
    -0.05
    going
    -0.05
     Jew
    -0.05
    ÙĪئ
    -0.05
    POSITIVE LOGITS
     minimum
    0.08
     ante
    0.07
     stakes
    0.07
    loth
    0.07
     Minimum
    0.07
     prices
    0.07
    minimum
    0.07
     Prices
    0.06
    FromFile
    0.06
    à¸±à¸Ľ
    0.06
    Activations Density 0.018%

    No Known Activations