© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41500
    Prev
    Next
    INDEX
    Explanations

    specific medical terminology or abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.09
    hta
    -0.08
    akte
    -0.08
    igid
    -0.07
    ampaign
    -0.07
    EDIUM
    -0.07
    -ÑĤо
    -0.07
    ocs
    -0.07
    iger
    -0.07
    inite
    -0.07
    POSITIVE LOGITS
    fully
    0.08
    edly
    0.08
    ev
    0.07
    arat
    0.07
    alist
    0.07
    âķĹ
    0.06
    most
    0.06
    lessly
    0.06
    hal
    0.06
    soever
    0.06
    Activations Density 0.004%

    No Known Activations