© 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. 5-LLAMASCOPE-RES-131K
    11. 125483
    Prev
    Next
    INDEX
    Explanations

    references to leisure activities and personal interests

    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
    icie
    -0.07
    itesse
    -0.07
    eldon
    -0.07
    جز
    -0.07
    uitka
    -0.07
    iffin
    -0.06
    .idea
    -0.06
    ackages
    -0.06
    ustum
    -0.06
     aracı
    -0.06
    POSITIVE LOGITS
    ISK
    0.07
    PF
    0.06
     pseud
    0.06
     cont
    0.06
     Chu
    0.06
     provision
    0.06
    æķ¦
    0.06
     enr
    0.06
     stretching
    0.06
     pseudo
    0.06
    Activations Density 0.011%

    No Known Activations