© 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. 105086
    Prev
    Next
    INDEX
    Explanations

    concepts related to sustainable development and social impact initiatives

    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
    weg
    -0.07
    rets
    -0.07
     Branch
    -0.07
    ाधन
    -0.07
    жд
    -0.07
    áž
    -0.07
    ẹp
    -0.06
    DSA
    -0.06
     Spo
    -0.06
    ÄįÃŃ
    -0.06
    POSITIVE LOGITS
     change
    0.13
    change
    0.11
     changes
    0.11
     CHANGE
    0.10
     Change
    0.09
     improvements
    0.09
    -change
    0.09
    _change
    0.09
    Change
    0.09
     Changes
    0.08
    Activations Density 0.024%

    No Known Activations