© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126041
    Prev
    Next
    INDEX
    Explanations

    structured legal or regulatory texts, particularly those related to U.S. law

    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
    essler
    -0.06
    281
    -0.06
     Wheel
    -0.06
    997
    -0.06
     pud
    -0.06
     Ober
    -0.06
     Bare
    -0.05
    bial
    -0.05
     pun
    -0.05
     Cad
    -0.05
    POSITIVE LOGITS
    ontrol
    0.07
    /icons
    0.07
    å³°
    0.07
    mast
    0.06
     mast
    0.06
    dej
    0.06
     leo
    0.06
    google
    0.06
    arios
    0.06
    wig
    0.06
    Activations Density 0.003%

    No Known Activations