© 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. 15-LLAMASCOPE-RES-131K
    11. 90557
    Prev
    Next
    INDEX
    Explanations

    phrases related to active participation and involvement

    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
    -Sah
    -0.08
    خاÙĨÙĩ
    -0.08
    orida
    -0.08
    stras
    -0.08
    cedures
    -0.08
    occo
    -0.07
    ahoma
    -0.07
    ëĭĿ
    -0.07
    oster
    -0.07
    atonin
    -0.07
    POSITIVE LOGITS
    able
    0.08
    ables
    0.07
     engagement
    0.07
    kel
    0.07
    /disable
    0.07
    force
    0.06
    941
    0.06
    ment
    0.06
    /support
    0.06
    oug
    0.06
    Activations Density 0.014%

    No Known Activations