© 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. 15-LLAMASCOPE-RES-131K
    11. 87546
    Prev
    Next
    INDEX
    Explanations

    phrases indicating associations and relationships in medical research findings

    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
    inis
    -0.08
    abaj
    -0.08
    awan
    -0.08
    alice
    -0.08
    occo
    -0.08
    .Side
    -0.07
    uebas
    -0.07
    apolis
    -0.07
    wap
    -0.07
    andel
    -0.07
    POSITIVE LOGITS
    ki
    0.06
     mul
    0.05
     Mul
    0.05
     Nut
    0.05
     Dunk
    0.05
    ãĤ¸ãĤª
    0.05
     Away
    0.05
     Twilight
    0.05
     ~
    0.05
     poss
    0.05
    Activations Density 0.003%

    No Known Activations