© 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. 58048
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory terms related to business partnerships

    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
    coni
    -0.07
    ujet
    -0.07
    ë°ĺ
    -0.07
    arget
    -0.07
    ванов
    -0.07
     derec
    -0.06
    ĭ
    -0.06
    ç»ĩ
    -0.06
    umo
    -0.06
     suspects
    -0.06
    POSITIVE LOGITS
     state
    0.07
    opleft
    0.07
    state
    0.07
     State
    0.06
    -state
    0.06
    atisfied
    0.06
     gutter
    0.06
     Dun
    0.06
    imensional
    0.06
    State
    0.06
    Activations Density 0.005%

    No Known Activations