© 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. 120085
    Prev
    Next
    INDEX
    Explanations

    words related to community service and engagement

    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
    ìŀ¡
    -0.09
    eyle
    -0.08
    )(__
    -0.07
    ostel
    -0.07
    ependency
    -0.07
     wards
    -0.07
     hâl
    -0.07
    estructor
    -0.07
    avras
    -0.07
     ЧаÑģ
    -0.07
    POSITIVE LOGITS
    vor
    0.06
     DM
    0.06
    ond
    0.06
    ilit
    0.06
     Parad
    0.05
     Stream
    0.05
     parad
    0.05
     mal
    0.05
    erm
    0.05
     cann
    0.05
    Activations Density 0.004%

    No Known Activations