© 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. 17213
    Prev
    Next
    INDEX
    Explanations

    references to pharmaceutical terms and entities, particularly those related to pharmacy benefit managers

    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
    s
    -0.14
    Ùĩ
    -0.11
    ska
    -0.08
    à¸Ĺ
    -0.08
    sik
    -0.08
    sense
    -0.07
    soc
    -0.07
    sah
    -0.07
    nt
    -0.07
    umbo
    -0.07
    POSITIVE LOGITS
    oti
    0.07
    aurus
    0.07
    theless
    0.07
    ³
    0.07
    erator
    0.06
    oj
    0.06
    ettes
    0.06
    маÑħ
    0.06
    aign
    0.06
    enant
    0.06
    Activations Density 0.191%

    No Known Activations