© 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. 104668
    Prev
    Next
    INDEX
    Explanations

    references to performance-enhancing substances and their effects in sports

    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
    aba
    -0.07
    phis
    -0.07
     aba
    -0.07
     Lum
    -0.06
    adge
    -0.06
    ibri
    -0.06
    teg
    -0.06
     Lehr
    -0.06
    abilities
    -0.06
    ongyang
    -0.06
    POSITIVE LOGITS
    andro
    0.09
     Arnold
    0.08
     femin
    0.08
    osterone
    0.08
    abolic
    0.07
    ZO
    0.07
     steroid
    0.07
     mascul
    0.07
    abs
    0.07
    rost
    0.07
    Activations Density 0.002%

    No Known Activations