© 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. 40911
    Prev
    Next
    INDEX
    Explanations

    phrases related to conferences and professional development events

    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
    iT
    -0.07
    iani
    -0.07
    /drivers
    -0.07
    outil
    -0.07
    (describing
    -0.07
    ùa
    -0.07
     Slice
    -0.07
     é¦ĸ页
    -0.07
    inox
    -0.07
    :disable
    -0.07
    POSITIVE LOGITS
     open
    0.08
     session
    0.07
     sessions
    0.07
     opportunity
    0.07
     industry
    0.06
    aget
    0.06
     Kid
    0.06
     interact
    0.06
     round
    0.06
    elan
    0.06
    Activations Density 0.018%

    No Known Activations