© 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. 128823
    Prev
    Next
    INDEX
    Explanations

    phrases related to the sharing and protection of 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
    .FileSystem
    -0.07
    éļ
    -0.07
    ANDOM
    -0.07
    .pivot
    -0.07
     Yön
    -0.07
    vise
    -0.07
    elib
    -0.07
    ÑĥÑĩа
    -0.06
    oure
    -0.06
    ¼
    -0.06
    POSITIVE LOGITS
     others
    0.10
     anyone
    0.10
     outside
    0.09
     other
    0.09
     nor
    0.09
     external
    0.08
     third
    0.08
     anything
    0.08
     anybody
    0.08
     any
    0.08
    Activations Density 0.003%

    No Known Activations