© 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. 74243
    Prev
    Next
    INDEX
    Explanations

    elements related to empowerment and support for at-risk youth

    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
    ãĤ¤ãĥĦ
    -0.07
    íĹĮ
    -0.07
    addy
    -0.07
     bulk
    -0.07
    party
    -0.07
     Bulk
    -0.07
    efe
    -0.06
    iso
    -0.06
    -io
    -0.06
    bulk
    -0.06
    POSITIVE LOGITS
     dign
    0.07
     themselves
    0.07
     dignity
    0.07
     stable
    0.07
     families
    0.07
     self
    0.07
     life
    0.07
     healthier
    0.07
     independence
    0.06
    stable
    0.06
    Activations Density 0.020%

    No Known Activations