© 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. 88144
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulatory actions and investigations

    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
    addock
    -0.07
    .IContainer
    -0.07
    δή
    -0.07
    ipple
    -0.06
    Ĥ¬
    -0.06
     propertyName
    -0.06
     english
    -0.06
    Ñģед
    -0.06
    .getZ
    -0.06
    å®ŀæĸ½
    -0.06
    POSITIVE LOGITS
     investigation
    0.14
     Investigation
    0.11
     investigating
    0.11
     investigations
    0.11
    invest
    0.10
     investigate
    0.10
     investigates
    0.09
     investigated
    0.09
     Investigations
    0.09
     investigators
    0.09
    Activations Density 0.028%

    No Known Activations