© 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. 62512
    Prev
    Next
    INDEX
    Explanations

    references to the Constitution and related legal documents

    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
     Gorgeous
    -0.06
    ogue
    -0.06
    bage
    -0.06
    би
    -0.05
    aded
    -0.05
     Spicer
    -0.05
     Hus
    -0.05
    enso
    -0.05
    ä¹İ
    -0.05
     Pens
    -0.05
    POSITIVE LOGITS
    ally
    0.09
    /XML
    0.08
    enstein
    0.07
    ALLY
    0.07
    Ìĥ
    0.07
    ezi
    0.07
    _ASSUME
    0.07
    alyzed
    0.07
    avras
    0.07
    eum
    0.07
    Activations Density 0.007%

    No Known Activations