© 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. 61838
    Prev
    Next
    INDEX
    Explanations

    mentions of drugging and poisoning

    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
     Tobacco
    -0.06
     lux
    -0.06
     Lux
    -0.06
     tez
    -0.06
    asel
    -0.06
     clearance
    -0.06
    ıs
    -0.05
    Interpolator
    -0.05
    èĴ
    -0.05
    adh
    -0.05
    POSITIVE LOGITS
    enburg
    0.07
     poisoned
    0.07
    undi
    0.07
    иÑĨин
    0.07
    ilent
    0.07
    ROTO
    0.07
    {lng
    0.07
    owers
    0.07
    rops
    0.07
    ÙĦØ·
    0.07
    Activations Density 0.020%

    No Known Activations