© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 526
    Prev
    Next
    INDEX
    Explanations

    specific concepts related to human rights and societal structures

    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
    enburg
    -0.06
    hurst
    -0.06
    ;element
    -0.06
    onavir
    -0.06
    <fieldset
    -0.06
    ONUS
    -0.06
    lius
    -0.06
    omik
    -0.06
    zones
    -0.06
    mania
    -0.06
    POSITIVE LOGITS
    .getElements
    0.07
    elerik
    0.07
    rather
    0.07
    /includes
    0.06
     nature
    0.06
    оби
    0.06
    addtogroup
    0.06
     rather
    0.06
    _particles
    0.06
    /ubuntu
    0.06
    Activations Density 0.034%

    No Known Activations