© 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. 86525
    Prev
    Next
    INDEX
    Explanations

    numeric data related to healthcare and organ donation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Headlines or article titles that appear between paragraphs of news content, often followed by a second set of angle brackets that mark the beginning of the article body.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    oter
    -0.07
    aptive
    -0.06
    ãĤ¤ãĤ¯
    -0.06
    Ø®ÙĪاÙĨ
    -0.06
    uckle
    -0.06
    imas
    -0.05
    agt
    -0.05
    rike
    -0.05
    adel
    -0.05
    alian
    -0.05
    POSITIVE LOGITS
    ̣
    0.07
    inish
    0.07
    steam
    0.07
     Till
    0.07
    ỡ
    0.07
    ü
    0.06
    üns
    0.06
     æ¹
    0.06
    ÏĦικα
    0.06
    undles
    0.06
    Activations Density 0.007%

    No Known Activations