© 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. 71850
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial management and accounting practices

    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
    دارÛĮ
    -0.09
    -Za
    -0.08
    łéĻ¤
    -0.07
    .pivot
    -0.07
    ponents
    -0.07
    _ascii
    -0.07
    Ł
    -0.07
    PÅĻed
    -0.07
    iability
    -0.07
    á»IJ
    -0.07
    POSITIVE LOGITS
     hire
    0.14
     consult
    0.12
     hires
    0.12
     hiring
    0.12
     hired
    0.11
     consulting
    0.11
     Hire
    0.11
    consult
    0.11
     consulted
    0.10
     consultation
    0.10
    Activations Density 0.113%

    No Known Activations