© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 59013
    Prev
    Next
    INDEX
    Explanations

    phrases related to surveillance and data privacy

    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
    omen
    -0.07
    inaire
    -0.07
    oding
    -0.07
     Coding
    -0.07
    ANC
    -0.07
    ADER
    -0.07
    ANNEL
    -0.07
    EY
    -0.07
    hev
    -0.07
    æĭī
    -0.06
    POSITIVE LOGITS
     contents
    0.07
     private
    0.06
    ificio
    0.06
    /misc
    0.06
    ä»»
    0.06
     weakness
    0.06
     confidential
    0.06
     user
    0.06
     ä»»
    0.06
     ì·¨
    0.06
    Activations Density 0.014%

    No Known Activations