© 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. 57209
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and regulatory aspects of business 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
    isper
    -0.08
    orias
    -0.07
    Ø®ÛĮ
    -0.06
    aleb
    -0.06
    zes
    -0.06
    azer
    -0.06
    ãģ£ãģ
    -0.06
    ostel
    -0.06
    edla
    -0.06
    =dict
    -0.06
    POSITIVE LOGITS
     whether
    0.14
    æĺ¯åIJ¦
    0.11
    whether
    0.11
     Whether
    0.10
    Whether
    0.10
     extent
    0.09
     degree
    0.09
     WHETHER
    0.09
     how
    0.08
     æĺ¯åIJ¦
    0.08
    Activations Density 0.029%

    No Known Activations