© 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. 28705
    Prev
    Next
    INDEX
    Explanations

    references to travel and experiences related to transportation

    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
    κε
    -0.07
    olini
    -0.07
    rophe
    -0.06
    ebin
    -0.06
    odka
    -0.06
    ẩy
    -0.06
    ingroup
    -0.06
    лÑĥг
    -0.06
    ichert
    -0.06
     lived
    -0.06
    POSITIVE LOGITS
     entertainment
    0.09
     Entertainment
    0.08
    oyer
    0.07
     bored
    0.07
     boredom
    0.07
     distraction
    0.07
     entert
    0.07
     entertain
    0.07
     passengers
    0.07
    auge
    0.07
    Activations Density 0.025%

    No Known Activations