© 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. 42637
    Prev
    Next
    INDEX
    Explanations

    terms related to medical symptoms and conditions

    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
    ropolis
    -0.09
    retty
    -0.07
    ython
    -0.07
    .pref
    -0.07
    igm
    -0.07
    åĨ
    -0.07
    iedy
    -0.07
    /km
    -0.07
    Ïħμ
    -0.06
    hiba
    -0.06
    POSITIVE LOGITS
    otos
    0.07
    Allocate
    0.06
    nett
    0.06
    nos
    0.06
     helicopt
    0.06
     Hughes
    0.06
    ã
    0.05
    ÑĢиÑĩ
    0.05
    atest
    0.05
    .mozilla
    0.05
    Activations Density 0.000%

    No Known Activations