© 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. 15-LLAMASCOPE-RES-131K
    11. 87527
    Prev
    Next
    INDEX
    Explanations

    phrases concerning legal rights and due process violations

    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
    _TestCase
    -0.07
     numberWith
    -0.07
     Middleton
    -0.07
    ãĤ§
    -0.07
    ãģĩ
    -0.07
    raq
    -0.06
    eded
    -0.06
    duino
    -0.06
    picker
    -0.06
    _MACRO
    -0.06
    POSITIVE LOGITS
     fairness
    0.09
     fair
    0.08
     Fair
    0.08
    Fair
    0.07
     opportunity
    0.07
    fair
    0.06
     Salv
    0.06
    ibal
    0.06
     unfair
    0.06
     warning
    0.06
    Activations Density 0.094%

    No Known Activations