© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16454
    Prev
    Next
    INDEX
    Explanations

    financial and contractual terms related to business agreements

    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
    unes
    -0.08
    ober
    -0.07
    ÏĩÏĮ
    -0.07
    Ïģαν
    -0.06
    _PATCH
    -0.06
    .snap
    -0.06
    .sock
    -0.06
    jure
    -0.06
    iffin
    -0.06
    cheme
    -0.06
    POSITIVE LOGITS
     transaction
    0.07
    /terms
    0.06
     press
    0.06
     rab
    0.06
    aux
    0.06
     deal
    0.06
     undisclosed
    0.06
     spokesman
    0.06
     Transaction
    0.06
     dint
    0.06
    Activations Density 0.002%

    No Known Activations