© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 75454
    Prev
    Next
    INDEX
    Explanations

    terms related to anti-drug efforts and illicit substances

    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
    ohl
    -0.07
    iy
    -0.07
    سر
    -0.07
    Ñĥди
    -0.07
    orial
    -0.06
    ij
    -0.06
    ii
    -0.06
    олеÑĤ
    -0.06
    forge
    -0.06
    606
    -0.06
    POSITIVE LOGITS
     measures
    0.07
    ifr
    0.07
     activity
    0.07
     Haven
    0.07
    æݪæĸ½
    0.06
     measure
    0.06
     activities
    0.06
     antibodies
    0.06
    plash
    0.06
    .scalablytyped
    0.06
    Activations Density 0.025%

    No Known Activations