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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28771
    Prev
    Next
    INDEX
    Explanations

    references to drug-related issues and substance abuse

    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
    854
    -0.07
     canv
    -0.07
    roke
    -0.06
     vit
    -0.06
    icast
    -0.06
     Essential
    -0.06
    fund
    -0.06
    agina
    -0.06
    oga
    -0.06
    unct
    -0.06
    POSITIVE LOGITS
     drugs
    0.11
     substances
    0.10
     recreational
    0.08
     Schedule
    0.08
     chemicals
    0.08
     addictive
    0.07
     misuse
    0.07
     substance
    0.07
    ëĭī
    0.07
     Drugs
    0.07
    Activations Density 0.023%

    No Known Activations