© 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. 40913
    Prev
    Next
    INDEX
    Explanations

    references to taking a moment to reflect or contemplate

    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
    596
    -0.06
    uste
    -0.06
    beb
    -0.06
    StackSize
    -0.06
    pton
    -0.06
    esser
    -0.06
    æķ·
    -0.06
    WS
    -0.05
    roke
    -0.05
    opes
    -0.05
    POSITIVE LOGITS
    ìĶ©
    0.09
    -long
    0.07
     nữa
    0.07
     Sole
    0.07
    ãĤ¿ãĥ«
    0.07
    گاÙĩ
    0.07
    _scheme
    0.07
    _Framework
    0.07
     ago
    0.07
    mars
    0.07
    Activations Density 0.006%

    No Known Activations