© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 86653
    Prev
    Next
    INDEX
    Explanations

    themes of social justice and advocacy for marginalized voices

    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
    _BS
    -0.06
    çon
    -0.06
    zel
    -0.06
    weise
    -0.06
    eyin
    -0.06
    atcher
    -0.06
    çģŃ
    -0.06
    uzey
    -0.06
    еÑĢÑĮ
    -0.06
    olib
    -0.06
    POSITIVE LOGITS
     millions
    0.11
     those
    0.11
     thousands
    0.10
     countless
    0.10
     others
    0.10
    éĤ£äºĽ
    0.09
     all
    0.09
     Thousands
    0.09
     hundreds
    0.09
    ousands
    0.09
    Activations Density 0.069%

    No Known Activations