© 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. 71246
    Prev
    Next
    INDEX
    Explanations

    keywords associated with crime and law enforcement controversies

    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
    imar
    -0.07
    ensa
    -0.07
    ecycle
    -0.07
    usch
    -0.07
    unch
    -0.06
     Ù¾ÛĮ
    -0.06
    erah
    -0.06
     Baghd
    -0.06
    606
    -0.06
     Swinger
    -0.06
    POSITIVE LOGITS
     pronto
    0.06
     NOI
    0.06
    ãģĸ
    0.06
    itom
    0.06
    \brief
    0.06
    odzi
    0.06
    orial
    0.06
     Hue
    0.06
     divisible
    0.06
    ãĤº
    0.06
    Activations Density 0.001%

    No Known Activations