© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 82737
    Prev
    Next
    INDEX
    Explanations

    discussions related to organizational efficiency and change

    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
    ifen
    -0.08
    askell
    -0.07
    readcr
    -0.07
    ouser
    -0.07
    InnerHTML
    -0.07
     stalled
    -0.07
     {?>↵
    -0.06
    inx
    -0.06
    rix
    -0.06
     harness
    -0.06
    POSITIVE LOGITS
     suddenly
    0.08
     becoming
    0.07
     become
    0.07
     obsolete
    0.07
     becomes
    0.07
    avir
    0.07
     quaint
    0.07
     Suddenly
    0.07
     tomorrow
    0.07
    unned
    0.07
    Activations Density 0.031%

    No Known Activations