© 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. 123304
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare improvement and access

    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
    欧ç¾İ
    -0.08
    عا
    -0.08
    ANGLES
    -0.08
    ä»Ķ
    -0.08
    ãĤĥ
    -0.07
    estre
    -0.07
    INCLUDING
    -0.07
    ãĥ³ãĥĸ
    -0.07
    çĥ§
    -0.07
     åı·
    -0.07
    POSITIVE LOGITS
     bl
    0.06
     otherwise
    0.06
     projects
    0.06
     atmos
    0.06
    9
    0.06
    El
    0.06
    è²´
    0.06
     El
    0.05
     infrastructure
    0.05
     barriers
    0.05
    Activations Density 0.033%

    No Known Activations