© 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. 17-LLAMASCOPE-RES-131K
    6. 129493
    Prev
    Next
    INDEX
    Explanations

    references to the movement and regulation of substances, particularly in relation to health effects

    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
     ChÃŃ
    -0.08
    ãĥ¼ãĥij
    -0.07
    ABCDEFGHIJKLMNOP
    -0.07
    acci
    -0.07
    ISTORY
    -0.07
     inval
    -0.07
    cion
    -0.07
    orr
    -0.07
    Ïİ
    -0.07
    essel
    -0.07
    POSITIVE LOGITS
     indeed
    0.07
    ury
    0.07
    ore
    0.06
     stake
    0.06
    roker
    0.06
    agne
    0.06
     both
    0.06
     DNA
    0.06
    ih
    0.06
     certain
    0.06
    Activations Density 0.023%

    No Known Activations