© 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. 120759
    Prev
    Next
    INDEX
    Explanations

    references to violence or violations of human rights

    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
    erras
    -0.07
     /^\
    -0.07
    ackle
    -0.07
     erken
    -0.07
    ért
    -0.07
    znam
    -0.07
    人åı£
    -0.06
    ching
    -0.06
    Łèĥ½
    -0.06
    atile
    -0.06
    POSITIVE LOGITS
     Report
    0.09
     report
    0.09
     often
    0.08
     many
    0.08
    æľīçļĦ
    0.08
     souvent
    0.08
    .gdx
    0.07
     sometimes
    0.07
    Report
    0.07
     reports
    0.07
    Activations Density 0.057%

    No Known Activations