© 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. 26559
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize collective experiences or generalizations about society

    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
    cul
    -0.07
    arian
    -0.07
    oplast
    -0.07
    .)↵↵↵↵
    -0.07
    asu
    -0.07
    il
    -0.07
    iki
    -0.07
    çīĪ
    -0.06
    ÛĮات
    -0.06
    lus
    -0.06
    POSITIVE LOGITS
     sake
    0.09
     reasons
    0.09
     purposes
    0.09
     despite
    0.07
     Despite
    0.07
    acas
    0.07
     spite
    0.06
    ecn
    0.06
     reason
    0.06
     cres
    0.06
    Activations Density 0.004%

    No Known Activations