© 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. 72336
    Prev
    Next
    INDEX
    Explanations

    terms related to social responsibility and community service

    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
    ipe
    -0.07
    ayi
    -0.07
     noct
    -0.07
    elman
    -0.06
    omentum
    -0.06
    dera
    -0.06
    184
    -0.06
    _lv
    -0.06
     oder
    -0.06
    iet
    -0.06
    POSITIVE LOGITS
     throughout
    0.10
     whenever
    0.08
    enever
    0.08
     afin
    0.08
     wherever
    0.08
     Throughout
    0.08
    herits
    0.07
     every
    0.07
     ensure
    0.07
     our
    0.07
    Activations Density 0.036%

    No Known Activations