© 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 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. 94231
    Prev
    Next
    INDEX
    Explanations

    references to social concepts and issues related to morality and political correctness

    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
    izo
    -0.08
     Khoa
    -0.07
    izi
    -0.06
    Ñħа
    -0.06
    icies
    -0.06
    uhl
    -0.06
    ozÃŃ
    -0.06
    ProgressHUD
    -0.06
     plan
    -0.06
    .BLUE
    -0.06
    POSITIVE LOGITS
     Axel
    0.09
    ariat
    0.07
    .ct
    0.07
    .hs
    0.07
     policing
    0.07
     consensus
    0.07
     Canary
    0.06
     Universities
    0.06
    .Networking
    0.06
    Ax
    0.06
    Activations Density 0.001%

    No Known Activations