© 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. 22-LLAMASCOPE-RES-131K
    11. 3920
    Prev
    Next
    INDEX
    Explanations

    references to historical political figures and events related to totalitarianism

    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
    ëĦIJ
    -0.07
    ENCIL
    -0.07
    eldo
    -0.07
    вод
    -0.07
     Haram
    -0.07
    ihad
    -0.07
    .UnitTesting
    -0.07
    obili
    -0.06
    íĩ´
    -0.06
    _FOREACH
    -0.06
    POSITIVE LOGITS
     pur
    0.14
     purge
    0.13
     Stalin
    0.10
    pur
    0.10
     Pur
    0.10
     PUR
    0.10
     camps
    0.09
    PUR
    0.08
     camp
    0.08
     regime
    0.08
    Activations Density 0.058%

    No Known Activations