© 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. 70597
    Prev
    Next
    INDEX
    Explanations

    terms related to surveillance and monitoring activities

    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
    loff
    -0.08
    anela
    -0.07
    .scalablytyped
    -0.07
    /stdc
    -0.07
    elix
    -0.07
    amaño
    -0.07
    edReader
    -0.07
    اÙĤÙĦ
    -0.07
    åde
    -0.07
    ÙĨتÛĮ
    -0.07
    POSITIVE LOGITS
     ver
    0.06
    itle
    0.06
    -twitter
    0.06
     suspicious
    0.05
    iel
    0.05
    ikh
    0.05
    éĴ
    0.05
     Alic
    0.05
    vt
    0.05
     ÑģвеÑĢ
    0.05
    Activations Density 0.000%

    No Known Activations