© 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. 128370
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to healthcare challenges and systemic issues

    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
     Sesso
    -0.09
    .scalablytyped
    -0.08
    fell
    -0.07
     abych
    -0.07
    -extra
    -0.07
     olsun
    -0.07
    £½
    -0.07
    iator
    -0.06
    loff
    -0.06
    apse
    -0.06
    POSITIVE LOGITS
     etc
    0.08
     leading
    0.08
     due
    0.07
     sometimes
    0.07
     drift
    0.07
     or
    0.07
    stown
    0.07
     resulting
    0.06
     often
    0.06
    etc
    0.06
    Activations Density 0.050%

    No Known Activations