© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 108942
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical trial methodology

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    297
    -0.07
    undry
    -0.06
    Unsafe
    -0.06
    UNDLE
    -0.06
    yas
    -0.06
    ateg
    -0.06
    oard
    -0.05
    .il
    -0.05
    Criteria
    -0.05
     slug
    -0.05
    POSITIVE LOGITS
    anza
    0.09
     study
    0.07
    -blind
    0.07
     controlled
    0.07
    ochen
    0.07
    ÏĦÏģι
    0.07
     Null
    0.07
    study
    0.07
    controlled
    0.07
     comparison
    0.06
    Activations Density 0.006%

    No Known Activations