© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89383
    Prev
    Next
    INDEX
    Explanations

    terms related to illicit drug use and associated transactions 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
    jeme
    -0.09
    atik
    -0.08
    ghi
    -0.08
    neau
    -0.08
    chyb
    -0.08
    elon
    -0.08
     annon
    -0.08
    _tD
    -0.08
    bsolute
    -0.08
    uchs
    -0.08
    POSITIVE LOGITS
     Laur
    0.06
    663
    0.05
     dep
    0.05
     several
    0.05
     numerous
    0.05
     ac
    0.05
    vala
    0.05
     burner
    0.05
     documents
    0.05
    om
    0.05
    Activations Density 0.011%

    No Known Activations