© 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. 75494
    Prev
    Next
    INDEX
    Explanations

    mentions of events or occurrences related to reunions or returns

    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
     Reverse
    -0.07
    ENAME
    -0.07
     reverse
    -0.07
    inition
    -0.07
    reverse
    -0.06
    912
    -0.06
    ONGO
    -0.06
    ifik
    -0.06
    fur
    -0.06
    Locker
    -0.06
    POSITIVE LOGITS
     return
    0.19
     returning
    0.17
     returns
    0.17
     returned
    0.17
    return
    0.16
     comeback
    0.16
     Returns
    0.15
    åĽŀæĿ¥
    0.14
     resumed
    0.14
     Return
    0.14
    Activations Density 0.072%

    No Known Activations