© 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. 15-LLAMASCOPE-RES-131K
    11. 26672
    Prev
    Next
    INDEX
    Explanations

    words related to health and wellness recommendations

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

    Character sequences that might be mistaken for HTML tags or code elements in multilingual content, especially common in poorly formatted or machine-translated text.

    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
    ÃŃrk
    -0.07
    ¤íĶĦ
    -0.07
    znik
    -0.07
    Ĭ
    -0.06
    yon
    -0.06
    vfs
    -0.06
    idar
    -0.06
     cookie
    -0.06
     intim
    -0.06
    hear
    -0.06
    POSITIVE LOGITS
    709
    0.08
    errupted
    0.07
    å¼ķ
    0.07
    -ÐĽ
    0.07
    èIJ½
    0.06
    ofday
    0.06
    UTO
    0.06
    Luck
    0.06
    ови
    0.06
    rary
    0.06
    Activations Density 0.031%

    No Known Activations