© 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. 86906
    Prev
    Next
    INDEX
    Explanations

    references to actors reprising their roles in a film series

    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
    ÑĪив
    -0.07
    abad
    -0.07
    ãĥ³ãĥIJ
    -0.07
    çIJ
    -0.07
    eday
    -0.07
    ượt
    -0.07
    isk
    -0.07
    abox
    -0.06
     Hein
    -0.06
    adil
    -0.06
    POSITIVE LOGITS
     repr
    0.09
     again
    0.08
     contract
    0.07
    åĨį
    0.07
     appearances
    0.07
     confirmed
    0.07
    again
    0.06
     feature
    0.06
     re
    0.06
     continue
    0.06
    Activations Density 0.014%

    No Known Activations