© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90801
    Prev
    Next
    INDEX
    Explanations

    keywords related to bio-weapons and biological research

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

    Technical or domain-specific terminology appearing in formal documents like research papers, patents, or technical documentation.

    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
     çĪ
    -0.07
    (Gravity
    -0.06
    cheng
    -0.06
    çłĶç©¶æīĢ
    -0.06
    oons
    -0.06
     اساسÛĮ
    -0.06
    adier
    -0.06
    ournals
    -0.06
    屬
    -0.06
    rons
    -0.06
    POSITIVE LOGITS
     friendly
    0.07
    ably
    0.07
    friendly
    0.07
    .arraycopy
    0.07
    -friendly
    0.06
    iev
    0.06
    quip
    0.06
    Īĺ
    0.06
     Friendly
    0.06
    pulse
    0.06
    Activations Density 0.462%

    No Known Activations