© 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. 70712
    Prev
    Next
    INDEX
    Explanations

    terms related to psychoactive substances and their effects

    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
     Mic
    -0.06
    isor
    -0.06
    ầm
    -0.06
     vit
    -0.06
     Mineral
    -0.06
    iff
    -0.05
    iece
    -0.05
     spot
    -0.05
     RSS
    -0.05
     mobility
    -0.05
    POSITIVE LOGITS
    ereum
    0.08
     Pey
    0.07
    WAY
    0.07
    наÑĢ
    0.07
     psychedelic
    0.07
    ãĥ³ãĥ
    0.07
    Ø®ÙĪ
    0.07
    .twig
    0.07
     Kosten
    0.07
     çłĶ
    0.07
    Activations Density 0.001%

    No Known Activations