© 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. 18278
    Prev
    Next
    INDEX
    Explanations

    references to human rights and related legal concepts

    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
    .toObject
    -0.06
    stab
    -0.06
     razor
    -0.06
    istra
    -0.06
     Pump
    -0.06
     prosecution
    -0.06
    UPPORT
    -0.06
     tar
    -0.06
     kontro
    -0.06
     Nationwide
    -0.06
    POSITIVE LOGITS
     human
    0.11
     Human
    0.11
    Human
    0.10
    human
    0.09
     rights
    0.09
     Rights
    0.08
     torture
    0.08
    Rights
    0.08
    -human
    0.08
     TORT
    0.08
    Activations Density 0.022%

    No Known Activations