© 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. 22-LLAMASCOPE-RES-131K
    11. 4000
    Prev
    Next
    INDEX
    Explanations

    terms related to urinary tract health and its associated infections

    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
     slab
    -0.07
    jeta
    -0.06
    å³
    -0.06
     dia
    -0.06
    cket
    -0.06
    orthand
    -0.06
     Wer
    -0.06
    celain
    -0.06
    èľĺèĽĽ
    -0.06
    tol
    -0.06
    POSITIVE LOGITS
     flag
    0.14
     cil
    0.13
    flag
    0.12
    -flag
    0.11
     Flag
    0.11
     flags
    0.11
     Swimming
    0.10
    Flag
    0.10
     mot
    0.10
     swimming
    0.10
    Activations Density 0.004%

    No Known Activations