© 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. 82806
    Prev
    Next
    INDEX
    Explanations

    references to human rights abuses and injustices

    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
    anzi
    -0.09
    ampus
    -0.08
    enen
    -0.08
     porr
    -0.07
    acock
    -0.07
    fos
    -0.07
    ilece
    -0.07
    lant
    -0.07
    chwitz
    -0.07
    umbn
    -0.07
    POSITIVE LOGITS
     often
    0.11
     sometimes
    0.09
    often
    0.09
     souvent
    0.08
     Often
    0.07
     usually
    0.07
     Sometimes
    0.07
    sometimes
    0.07
     oft
    0.07
    Often
    0.07
    Activations Density 0.006%

    No Known Activations