© 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. 15-LLAMASCOPE-RES-131K
    11. 87338
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement and security issues

    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
    loven
    -0.09
    roupon
    -0.09
    kiye
    -0.08
    mpar
    -0.08
    azon
    -0.08
    ока
    -0.08
    upal
    -0.08
    optera
    -0.08
    .Annotations
    -0.07
    KHTML
    -0.07
    POSITIVE LOGITS
     Morse
    0.06
     Patterson
    0.06
    FD
    0.05
     candid
    0.05
     FD
    0.05
     Crosby
    0.05
    ji
    0.05
     epis
    0.05
     -,
    0.05
     ourselves
    0.05
    Activations Density 0.029%

    No Known Activations