© 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. 15-LLAMASCOPE-RES-131K
    11. 977
    Prev
    Next
    INDEX
    Explanations

    references to ownership and transactions related to properties and businesses

    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
    pig
    -0.06
    createForm
    -0.06
    issa
    -0.06
    lya
    -0.06
    शन
    -0.06
    ÐľÐŀ
    -0.06
    άνÏī
    -0.06
    odge
    -0.06
     cân
    -0.06
    ti
    -0.06
    POSITIVE LOGITS
     ownership
    0.12
     Ownership
    0.10
    Ownership
    0.10
    ownership
    0.09
     owner
    0.09
     transfer
    0.07
    売
    0.07
    owner
    0.07
     owned
    0.07
    transfer
    0.06
    Activations Density 0.034%

    No Known Activations