© 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. 17-LLAMASCOPE-RES-131K
    11. 56691
    Prev
    Next
    INDEX
    Explanations

    terms associated with historical political imprisonment and dissent

    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
     Victorian
    -0.07
    uzzi
    -0.06
    enic
    -0.06
    äch
    -0.06
    oya
    -0.06
    eparator
    -0.06
    tz
    -0.06
    edi
    -0.06
    ury
    -0.06
    bole
    -0.06
    POSITIVE LOGITS
     Lithuania
    0.13
     Vil
    0.11
    .lt
    0.09
     Balt
    0.09
     Lith
    0.08
    inas
    0.08
     Baltic
    0.08
    Ä
    0.08
    .lv
    0.07
     Taipei
    0.07
    Activations Density 0.019%

    No Known Activations