© 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. 75859
    Prev
    Next
    INDEX
    Explanations

    phrases associated with events and participation in activities

    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
     Daily
    -0.07
     daily
    -0.06
     Later
    -0.06
     later
    -0.06
    Daily
    -0.06
     GOODMAN
    -0.05
     McKenzie
    -0.05
     premise
    -0.05
    ÑĤÑĢон
    -0.05
     Ts
    -0.05
    POSITIVE LOGITS
     lately
    0.20
     recently
    0.20
     recent
    0.19
    recent
    0.19
    ä»Ĭå¹´
    0.18
     Recently
    0.17
    Recently
    0.16
    æľĢè¿ij
    0.16
     Recent
    0.15
     ìĿ´ë²Ī
    0.14
    Activations Density 0.255%

    No Known Activations