© 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. 92943
    Prev
    Next
    INDEX
    Explanations

    phrases related to confidentiality and the protection of sensitive 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
    esseract
    -0.07
    è±Ĩ
    -0.07
    prak
    -0.07
    ög
    -0.06
    amon
    -0.06
    ived
    -0.06
    akit
    -0.06
    -syntax
    -0.06
    eterminate
    -0.06
    pite
    -0.06
    POSITIVE LOGITS
    communications
    0.07
     communications
    0.07
     communication
    0.07
    communication
    0.07
    ABA
    0.06
     privileged
    0.06
    ¶Ī
    0.06
     confidential
    0.06
     designated
    0.06
     conversations
    0.06
    Activations Density 0.006%

    No Known Activations