© 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. 103297
    Prev
    Next
    INDEX
    Explanations

    concepts related to natural rights and entitlements

    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
    amu
    -0.07
    Ïģε
    -0.06
     Feder
    -0.06
    indi
    -0.06
     Naked
    -0.06
     Bilder
    -0.06
    rawn
    -0.06
    anko
    -0.06
    eka
    -0.06
    ecess
    -0.06
    POSITIVE LOGITS
     Duty
    0.07
     duty
    0.07
    xCD
    0.06
    ellas
    0.06
    abol
    0.06
    443
    0.06
    ACHI
    0.06
     huy
    0.06
    inch
    0.06
    ering
    0.06
    Activations Density 0.012%

    No Known Activations