© 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. 63225
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and treatments, particularly those involving hormones and uterine health

    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
    \Carbon
    -0.07
    arter
    -0.07
    isson
    -0.07
    positor
    -0.07
    727
    -0.06
    åĿĬ
    -0.06
     APPLY
    -0.06
    CGFloat
    -0.06
     GANG
    -0.06
     Dating
    -0.06
    POSITIVE LOGITS
     women
    0.10
     Estr
    0.10
     estrogen
    0.10
     Women
    0.09
     men
    0.08
     estr
    0.08
     breast
    0.08
    Women
    0.08
     arom
    0.08
     femin
    0.07
    Activations Density 0.005%

    No Known Activations