© 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. 26881
    Prev
    Next
    INDEX
    Explanations

    medical terms related to inflammation and its measurements

    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
    aru
    -0.06
     lain
    -0.06
    iri
    -0.06
    hat
    -0.05
     since
    -0.05
    andre
    -0.05
    leta
    -0.05
    org
    -0.05
     long
    -0.05
    owell
    -0.05
    POSITIVE LOGITS
    à¸
    0.07
    Animate
    0.07
    ģn
    0.07
    ATOM
    0.07
    zew
    0.07
    Animating
    0.06
    adoo
    0.06
    semb
    0.06
    esome
    0.06
    emos
    0.06
    Activations Density 0.097%

    No Known Activations