© 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. 77278
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and their implications

    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
    asma
    -0.07
    anny
    -0.06
    fat
    -0.06
    kee
    -0.06
     es
    -0.06
    aspers
    -0.06
    steen
    -0.06
     rival
    -0.05
     const
    -0.05
     exposition
    -0.05
    POSITIVE LOGITS
    ãĥ¼ãĥ¬
    0.07
    .createClass
    0.07
    NotSupportedException
    0.07
    .ManyToMany
    0.07
    лÑĮÑĤ
    0.07
     Pill
    0.06
     Bü
    0.06
    ãĥ³ãĥĸ
    0.06
    .keywords
    0.06
     koc
    0.06
    Activations Density 0.000%

    No Known Activations