© 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. 77666
    Prev
    Next
    INDEX
    Explanations

    references to legal decisions and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Function words and phrases that create factual connections or establish relationships between statements, particularly in reporting, legal contexts, or formal declarations.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    æŃ£
    -0.07
    semi
    -0.06
    uhan
    -0.06
    ISA
    -0.06
    iaux
    -0.06
    uzz
    -0.06
    isa
    -0.06
    gnu
    -0.06
    à¸ķะ
    -0.06
    rane
    -0.06
    POSITIVE LOGITS
     Nope
    0.13
     rejection
    0.12
     reject
    0.11
     denial
    0.10
    åIJ¦
    0.10
     NO
    0.10
     failed
    0.10
     rejected
    0.10
     rejects
    0.10
    reject
    0.10
    Activations Density 0.212%

    No Known Activations