© 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. 59171
    Prev
    Next
    INDEX
    Explanations

    mentions of performance-enhancing drugs and related 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
    ого
    -0.07
    ckill
    -0.06
    ãĥ¼ãĥĩ
    -0.06
    enza
    -0.06
    bia
    -0.06
    tones
    -0.06
    REW
    -0.06
    assi
    -0.06
    VML
    -0.06
    dif
    -0.06
    POSITIVE LOGITS
     doping
    0.09
     drug
    0.08
     Drug
    0.08
    æľį
    0.08
    drug
    0.07
     Suspension
    0.07
     suspension
    0.07
    abolic
    0.07
    osterone
    0.07
    usp
    0.07
    Activations Density 0.038%

    No Known Activations