© 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. 17735
    Prev
    Next
    INDEX
    Explanations

    mentions of the software Pegasus and its implications in surveillance and targeting individuals

    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
    upe
    -0.07
    ione
    -0.07
    antine
    -0.06
    sek
    -0.06
    (strtolower
    -0.06
    kenin
    -0.06
    ogens
    -0.05
     Economy
    -0.05
    anken
    -0.05
    beit
    -0.05
    POSITIVE LOGITS
     target
    0.08
    utomation
    0.08
    target
    0.07
    ware
    0.07
    -target
    0.07
     surve
    0.07
     Target
    0.07
    Wildcard
    0.07
    Latch
    0.07
    ãĤ¤ãĤ¯
    0.07
    Activations Density 0.040%

    No Known Activations