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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127849
    Prev
    Next
    INDEX
    Explanations

    terms related to medical qualifications and research activities

    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
    wipe
    -0.07
    685
    -0.07
    chl
    -0.07
    iets
    -0.07
    lassen
    -0.07
    opak
    -0.07
    bias
    -0.07
    rvine
    -0.07
    æ
    -0.06
    eczy
    -0.06
    POSITIVE LOGITS
     Cancer
    0.10
     cancer
    0.09
     cancers
    0.08
     malign
    0.06
     HER
    0.06
     toler
    0.06
     tumors
    0.06
    ÎŃÏģα
    0.06
     Ki
    0.06
     kinase
    0.06
    Activations Density 0.011%

    No Known Activations