© 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. 76143
    Prev
    Next
    INDEX
    Explanations

    phrases related to claiming business expenses for tax purposes

    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
    à¤Ĥडल
    -0.07
    acus
    -0.07
    еви
    -0.06
    edback
    -0.06
    ани
    -0.06
     Dut
    -0.06
     Baum
    -0.06
    iked
    -0.06
    άνÏĦα
    -0.06
     mennes
    -0.06
    POSITIVE LOGITS
    åħģ
    0.06
    uhl
    0.06
    ama
    0.06
    509
    0.06
    oods
    0.06
     ble
    0.06
    ny
    0.06
    âĻł
    0.06
     trous
    0.06
     trav
    0.06
    Activations Density 0.046%

    No Known Activations