© 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. 127766
    Prev
    Next
    INDEX
    Explanations

    themes related to legal and regulatory complexities in business interactions

    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
    ivas
    -0.08
    icz
    -0.08
    omain
    -0.08
    idend
    -0.08
    andi
    -0.08
    821
    -0.07
    ubi
    -0.07
     INLINE
    -0.07
    icit
    -0.07
    706
    -0.07
    POSITIVE LOGITS
     different
    0.10
     multiple
    0.10
     complex
    0.09
    ä¸įåIJĮçļĦ
    0.08
     each
    0.07
     varying
    0.07
    different
    0.07
     often
    0.07
    multiple
    0.07
     potentially
    0.07
    Activations Density 0.035%

    No Known Activations