© 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. 15-LLAMASCOPE-RES-131K
    11. 88627
    Prev
    Next
    INDEX
    Explanations

    phrases related to prescription drugs and their disposal

    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
    zy
    -0.08
     fie
    -0.07
    ãĥ«ãĥĪ
    -0.07
    acula
    -0.07
    .Fat
    -0.07
    ennie
    -0.07
    aura
    -0.07
    erap
    -0.06
    raya
    -0.06
    atra
    -0.06
    POSITIVE LOGITS
    лиÑĪком
    0.07
     harmful
    0.06
    еÑĢо
    0.06
    .any
    0.06
     Kinh
    0.06
     dof
    0.06
     laure
    0.06
     nackte
    0.06
     any
    0.06
    uned
    0.06
    Activations Density 0.007%

    No Known Activations