© 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. 62465
    Prev
    Next
    INDEX
    Explanations

    themes related to societal responsibility and advocacy

    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
     DÄĽ
    -0.08
    ula
    -0.07
     ведÑĮ
    -0.07
    .trailing
    -0.07
    ä¼ģ
    -0.07
    ULA
    -0.07
    åĬ¿
    -0.07
     êµŃ민
    -0.07
     Oyun
    -0.07
    ulg
    -0.07
    POSITIVE LOGITS
     individual
    0.08
     individuals
    0.07
    lla
    0.07
    individual
    0.07
     specifically
    0.06
     world
    0.06
     particularly
    0.06
     indiv
    0.06
    us
    0.06
     Trends
    0.06
    Activations Density 0.041%

    No Known Activations