© 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. 17-LLAMASCOPE-RES-131K
    11. 59307
    Prev
    Next
    INDEX
    Explanations

    phrases related to pharmaceutical regulations and industry practices

    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
    ONENT
    -0.07
    asper
    -0.07
    abant
    -0.07
    luet
    -0.07
    agas
    -0.07
    isen
    -0.07
    dge
    -0.06
    illion
    -0.06
     consolid
    -0.06
    à¹Īาว
    -0.06
    POSITIVE LOGITS
     new
    0.08
     existing
    0.08
     training
    0.07
     compatible
    0.07
     infrastructure
    0.07
     software
    0.07
    new
    0.07
     Compatible
    0.07
     supporting
    0.07
    aur
    0.07
    Activations Density 0.028%

    No Known Activations