© 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. 69071
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to disease agents and pathogens

    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
    oran
    -0.08
     noh
    -0.07
    ÏģÏį
    -0.07
    fty
    -0.07
    hausen
    -0.07
    _consts
    -0.07
    ноÑģи
    -0.07
    .Reporting
    -0.07
    mpz
    -0.06
    chal
    -0.06
    POSITIVE LOGITS
    enn
    0.06
    enna
    0.06
    ela
    0.06
    ires
    0.06
    iform
    0.06
    aaS
    0.06
    aa
    0.06
    aaaa
    0.05
    /tree
    0.05
    endif
    0.05
    Activations Density 0.004%

    No Known Activations