© 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. 56224
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical and medicinal terms related to antibiotics and medications

    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
    cul
    -0.07
    991
    -0.07
     ÄĮer
    -0.07
    .apps
    -0.07
    hya
    -0.06
    328
    -0.06
     Obr
    -0.06
     yiy
    -0.06
    okus
    -0.06
    arg
    -0.06
    POSITIVE LOGITS
     gre
    0.07
    825
    0.07
    å¾
    0.07
    istrovstvÃŃ
    0.07
    .sourceforge
    0.06
    Lex
    0.06
    owo
    0.06
    FFE
    0.06
    atto
    0.06
    å®ľ
    0.06
    Activations Density 0.002%

    No Known Activations