© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 74362
    Prev
    Next
    INDEX
    Explanations

    references to organized crime and drug operations

    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
    roken
    -0.10
    xico
    -0.07
     î¡
    -0.07
    coli
    -0.07
    æĿ¯
    -0.07
    _DEFINE
    -0.07
    upa
    -0.06
    olet
    -0.06
    saldo
    -0.06
    roke
    -0.06
    POSITIVE LOGITS
     drug
    0.10
     Drug
    0.10
     drugs
    0.09
    drug
    0.08
    Drug
    0.08
     Drugs
    0.08
    nar
    0.08
     заклад
    0.07
     nar
    0.07
     DEA
    0.07
    Activations Density 0.028%

    No Known Activations