Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29436
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal agreements and obligations

    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
    513
    -0.07
     Imported
    -0.06
     nab
    -0.06
    iegel
    -0.06
    ä¸ĭæĿ¥
    -0.06
     editorial
    -0.06
     imported
    -0.06
    -vertical
    -0.05
     Luz
    -0.05
     intake
    -0.05
    POSITIVE LOGITS
     supplying
    0.13
     sending
    0.12
     supply
    0.11
     send
    0.11
     delivering
    0.10
    supply
    0.10
     entreg
    0.10
     deliver
    0.10
     sends
    0.10
    -send
    0.10
    Activations Density 0.048%

    No Known Activations