© 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. 117188
    Prev
    Next
    INDEX
    Explanations

    elements related to drug labeling and regulation

    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
    oulos
    -0.07
    NullOrEmpty
    -0.06
     wage
    -0.06
    ãĥĥãĤ¯
    -0.06
    edio
    -0.06
    ãĤĴãģĬ
    -0.06
    ookies
    -0.06
    ccoli
    -0.06
    meler
    -0.06
    ÄĽle
    -0.06
    POSITIVE LOGITS
     safety
    0.11
     Safety
    0.09
    afety
    0.09
    Safety
    0.09
    vol
    0.07
     NVIC
    0.07
    DDD
    0.07
     adverse
    0.06
     liver
    0.06
     compens
    0.06
    Activations Density 0.012%

    No Known Activations