© 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. 88100
    Prev
    Next
    INDEX
    Explanations

    references to financial misconduct and exploitation in legal contexts

    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
    lifetime
    -0.07
    .googlecode
    -0.06
    ("(%
    -0.06
    ÙĪبة
    -0.06
    uja
    -0.06
    893
    -0.06
    ekil
    -0.06
    å¿
    -0.06
     Diamonds
    -0.06
    æ¿ĥ
    -0.06
    POSITIVE LOGITS
     charges
    0.09
     charge
    0.07
     fee
    0.07
     billed
    0.07
     claimed
    0.07
     fees
    0.07
     claiming
    0.07
     services
    0.06
    _TUN
    0.06
     recover
    0.06
    Activations Density 0.015%

    No Known Activations