© 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 EvalsExportsinterp-engineNEWAPI 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. 105041
    Prev
    Next
    INDEX
    Explanations

    phrases related to data privacy and the implications of using personal information

    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
    éric
    -0.09
    estone
    -0.08
    /Dk
    -0.07
    ãĥĶãĥ¼
    -0.07
     Conservation
    -0.07
    ins
    -0.07
    NavController
    -0.07
    urai
    -0.07
    ckeditor
    -0.07
    mouseleave
    -0.07
    POSITIVE LOGITS
     identifiable
    0.07
     alone
    0.07
     easily
    0.07
     identify
    0.07
     identifying
    0.07
     ident
    0.07
     identification
    0.07
     identity
    0.07
     readily
    0.07
     uniquely
    0.06
    Activations Density 0.002%

    No Known Activations