© 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. 15-LLAMASCOPE-RES-131K
    11. 103554
    Prev
    Next
    INDEX
    Explanations

    legal and business-related terms, particularly those associated with different areas of law and transactions

    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
    roke
    -0.07
    atus
    -0.07
     Turnbull
    -0.07
    اÙĦÙī
    -0.07
    (CType
    -0.07
    undos
    -0.07
    LinkId
    -0.07
    ì¶
    -0.06
    é§
    -0.06
    lect
    -0.06
    POSITIVE LOGITS
    -related
    0.08
     matters
    0.07
     related
    0.07
     issues
    0.06
    	perror
    0.06
    utoff
    0.06
     clients
    0.06
     civ
    0.06
     division
    0.06
     Related
    0.06
    Activations Density 0.019%

    No Known Activations