© 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. 17-LLAMASCOPE-RES-131K
    11. 75920
    Prev
    Next
    INDEX
    Explanations

    references to health, wellness, and fitness-related topics

    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
    emey
    -0.07
    stoff
    -0.07
    unj
    -0.07
    attern
    -0.07
    اÙĨÙĩ
    -0.06
     Ekon
    -0.06
    ovice
    -0.06
    oden
    -0.06
    ÄĻż
    -0.06
    LETE
    -0.06
    POSITIVE LOGITS
     outweigh
    0.17
     outnumber
    0.15
     far
    0.12
    æ¯Ķ
    0.11
     greater
    0.11
     exceeds
    0.10
     outr
    0.10
    มาà¸ģà¸ģว
    0.10
    greater
    0.10
    far
    0.10
    Activations Density 0.136%

    No Known Activations