© 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. 60239
    Prev
    Next
    INDEX
    Explanations

    phrases related to artistic or cultural activities

    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
     nackte
    -0.07
    ëľ
    -0.07
    aptors
    -0.07
    obot
    -0.07
    -desc
    -0.06
    itz
    -0.06
    ansom
    -0.06
    lict
    -0.06
     Coord
    -0.06
     Chew
    -0.06
    POSITIVE LOGITS
     alongside
    0.15
     next
    0.13
     beside
    0.12
    æĹģ
    0.12
    next
    0.12
     neben
    0.11
     ÑĢÑıдом
    0.11
    -next
    0.10
     adjacent
    0.10
     neighbors
    0.10
    Activations Density 0.068%

    No Known Activations