© 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. 116440
    Prev
    Next
    INDEX
    Explanations

    demographic details and medical history of patients

    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
    бав
    -0.07
    cite
    -0.07
    utes
    -0.07
    ernen
    -0.07
     Cup
    -0.07
    avana
    -0.06
    بÙĪاسطة
    -0.06
    ato
    -0.06
    izon
    -0.06
    wers
    -0.06
    POSITIVE LOGITS
     presented
    0.06
    ë¡ľë¶ĢíĦ°
    0.06
    æ´
    0.06
    ãģŁãĤī
    0.06
    weight
    0.06
    éĻ¢
    0.06
    æĿŁ
    0.06
    plib
    0.06
    jango
    0.05
    ãĤ¸ãĤ¢
    0.05
    Activations Density 0.015%

    No Known Activations